The Glossary

abnormal return — defined in Session 8.6 · Event-Driven Strategies (coming soon)

accruals — defined in Session 8.5 · Value, Quality & Fundamental Quant (coming soon)

ACF — defined in Session 5.4 · Stationarity & ARMA Models (coming soon)

ADF test — defined in Session 5.4 · Stationarity & ARMA Models (coming soon)

adjusted price — defined in Session 4.3 · Corporate Actions, Security Master & Continuous Futures (coming soon)

adjustment factor — defined in Session 4.3 · Corporate Actions, Security Master & Continuous Futures (coming soon)

adversarial environment — defined in Session 12.1 · Why Finance ML Is Different (coming soon)

adverse selection — defined in Session 14.2 · Microstructure Models (coming soon)

aggregational Gaussianity — defined in Session 5.1 · Stylized Facts of Returns (coming soon)

alerting — defined in Session 15.5 · Operations & MLOps (coming soon)

Almgren-Chriss model — defined in Session 14.4 · Optimal Execution & TCA (coming soon)

alpha — the average excess return left after subtracting what a strategy's factor exposures earned; always relative to a chosen model. (Session 1.2)

alpha decay — the erosion of an edge over time as others trade it or markets change. (Session 1.3)

alternative data — defined in Session 13.1 · Alternative Data (coming soon)

American option — an option that can be exercised on any business day up to expiry (US single-stock and ETF options). (Session 2.7)

annualisation — rescaling to a yearly figure: mean × periods, volatility × √periods. (Session 2.3)

anomaly — a return pattern that known risks do not explain, usually traced to biases or constraints; trading can erode it. (Session 1.2)

antithetic variates — using every random draw Z together with −Z and averaging the pair; helps when the payoff moves one way with Z, hurts when it is symmetric. (Session 3.5)

Apache Arrow — defined in Session 4.5 · The Research Storage Stack (coming soon)

APT — defined in Session 7.2 · CAPM, APT & Factor Regressions (coming soon)

arbitrage — defined in Session 7.1 · Efficient Markets & the Limits to Arbitrage (coming soon)

ARMA model — defined in Session 5.4 · Stationarity & ARMA Models (coming soon)

arrival price — defined in Session 14.4 · Optimal Execution & TCA (coming soon)

as-of join — defined in Session 4.4 · Time, Calendars, As-of Joins & Bars (coming soon)

ask — the lowest price at which someone is currently willing to sell, with the size; also called the offer. (Session 2.1)

asset manager — a firm that invests pooled or segregated client money, mostly long-only, for a fee that is a percentage of assets. (Session 1.1)

authorised participant — a large dealer under contract with an ETF, allowed to create and redeem its shares in creation units. (Session 2.2)

auto-deleveraging — a venue's last resort when its insurance fund is exhausted: profitable opposing positions are closed, ranked by profit and leverage, to cover a bankrupt position. (Session 2.6)

autocorrelation — defined in Session 5.1 · Stylized Facts of Returns (coming soon)

automated market maker — a venue that quotes prices from a formula over pooled reserves, such as $x\,y = k$, instead of matching orders in a book. (Session 2.6)

autoregressive model — defined in Session 5.4 · Stationarity & ARMA Models (coming soon)

Avellaneda-Stoikov model — defined in Session 14.5 · Market Making (coming soon)

back-adjustment — defined in Session 4.3 · Corporate Actions, Security Master & Continuous Futures (coming soon)

backfill bias — defined in Session 4.2 · Point-in-Time Data & Data Biases (coming soon)

backtest — a simulation of how a trading rule would have performed on historical data. (Session 1.3)

backtest-to-live decay — the drop in performance (e.g. Sharpe ratio) between a strategy's backtest and its live trading, from overfitting, missed costs and edge erosion together. (Session 1.4)

backtest–live parity — defined in Session 6.3 · Build an Event-Driven Backtester (coming soon)

backwardation — futures below spot, the curve falling with maturity; not the same as Keynes's normal backwardation. (Session 2.4)

bag of words — defined in Session 13.2 · Text as Data (coming soon)

base rate — how often an outcome occurs in the reference class a case belongs to; the prior you start from before weighing the specifics of the case. (Session 1.4)

basis — spot minus futures, $S - F$ (this course's convention); zero at expiry. (Session 2.4)

batch-means standard error — the standard error of a statistic with no simple formula (a median, a quantile, a maximum drawdown): split the paths into batches, compute the statistic in each, and divide the standard deviation of the batch values by √(number of batches). (Session 3.5)

Bayes' rule — $\Prob(H \mid D) = \Prob(D \mid H)\,\Prob(H)/\Prob(D)$; turns how often the data appear when H is true into how likely H is given the data. (Session 3.1)

behavioural bias — defined in Session 7.1 · Efficient Markets & the Limits to Arbitrage (coming soon)

best execution — defined in Session 15.6 · Market Conduct & Compliance (coming soon)

bet sizing — choosing how much of your capital to stake on each bet; it decides whether an edge compounds or ruins you. (Session 3.6)

beta — a strategy's sensitivity to a factor: how much its return moves per unit move in the factor's return. (Session 1.2)

bid — the highest price at which someone is currently willing to buy, with the size they will buy. (Session 2.1)

bid-ask spread — ask minus bid: what an immediate round trip costs at the touch, before any fees. (Session 2.1)

binding constraint — a constraint that holds with equality at the optimum, as opposed to a slack one with room to spare. (Session 3.4)

binomial tree — defined in Session 10.1 · No-Arbitrage & Binomial Trees (coming soon)

Black-Litterman model — defined in Session 9.6 · Optimization with Constraints & Costs (coming soon)

Black-Scholes PDE — defined in Session 10.3 · Black-Scholes-Merton (coming soon)

Black-Scholes-Merton model — defined in Session 10.3 · Black-Scholes-Merton (coming soon)

block bootstrap — a bootstrap that resamples runs of consecutive observations instead of single points, so dependence within a block, such as volatility clustering, survives in the resample. (Session 3.5)

book-to-market ratio — defined in Session 8.5 · Value, Quality & Fundamental Quant (coming soon)

bootstrap — estimating the sampling distribution of a statistic by recomputing it on resamples of the data drawn with replacement; resample blocks of days when the data are dependent. (Session 3.5)

borrow cost — defined in Session 6.5 · Transaction Costs & Capacity (coming soon)

borrow fee — the annual rate, charged daily on the loan's value, that a short seller pays the lender; under 1% for most stocks, far more for hard-to-borrow ones. (Session 2.2)

brainteaser — defined in Session 16.2 · Interview Drills: Probability, Mental Math & Market-Making Games (coming soon)

breadth — defined in Session 8.7 · Combining Signals (coming soon)

break-even cost — defined in Session 6.5 · Transaction Costs & Capacity (coming soon)

breakpoints — defined in Session 7.3 · Building Factors: Sorts & Fama-MacBeth (coming soon)

broker — the firm that accepts your orders, checks them, sends them to venues for you, reports fills and holds your account. (Session 2.1)

broker API — defined in Session 15.3 · Broker APIs & FIX (coming soon)

Brownian bridge — the conditional distribution of a Brownian path between two known points; used here to recover the probability that a path dipped through a barrier between two observations that both lie above it. (Session 3.5)

Brownian motion — defined in Session 10.2 · Stochastic Calculus for Engineers (coming soon)

buy side — firms that invest capital and buy trading services to do it: asset managers, hedge funds, pensions, insurers. (Session 1.1)

call option — the right, not the obligation, to buy the underlying at the strike price, at or before expiry. (Session 2.7)

Calmar ratio — defined in Session 9.9 · Performance, Attribution & When to Switch Off (coming soon)

capacity — defined in Session 6.5 · Transaction Costs & Capacity (coming soon)

CAPM — defined in Session 7.2 · CAPM, APT & Factor Regressions (coming soon)

capstone project — defined in Session 16.5 · Capstone: Brief & Rubric (coming soon)

carry — defined in Session 8.4 · Carry Across Asset Classes (coming soon)

carry trade — defined in Session 8.4 · Carry Across Asset Classes (coming soon)

carry-to-risk ratio — defined in Session 8.4 · Carry Across Asset Classes (coming soon)

cash-and-carry arbitrage — borrowing to buy the asset and selling the future when the future is dearer than the carry price, locking in the gap. (Session 2.4)

causal graph — defined in Session 7.5 · Causal Factor Investing (coming soon)

central counterparty — a clearing house that becomes buyer to every seller and seller to every buyer (novation), backed by its members' margin. (Session 2.1)

central limit theorem — the standardised average of many independent draws with finite variance approaches a normal distribution, whatever the original shape; slowly when the tails are fat. (Session 3.1)

centralised exchange — a company that runs a crypto trading venue and is also broker, clearing house and custodian for its customers. (Session 2.6)

characteristic function — defined in Session 10.6 · Stochastic Volatility & Numerical Methods (coming soon)

Christoffersen test — defined in Session 9.7 · VaR, ES, EVT & VaR Backtests (coming soon)

CIR model — defined in Session 11.3 · Short-Rate Models & Swaps (coming soon)

clearing house — the institution that confirms, nets and guarantees trades between the trade and its settlement. (Session 2.1)

closing auction — defined in Session 14.1 · The Limit Order Book (coming soon)

clustered feature importance — defined in Session 12.5 · Feature Importance & Interpretability (coming soon)

cointegration — defined in Session 5.6 · Cointegration & Mean Reversion (coming soon)

collider — defined in Session 7.5 · Causal Factor Investing (coming soon)

colocation — defined in Session 14.6 · Latency & Performance Engineering (coming soon)

columnar storage — defined in Session 4.5 · The Research Storage Stack (coming soon)

combinatorial purged cross-validation — defined in Session 6.6 · Validation: Walk-Forward, Purged K-Fold & CPCV (coming soon)

commission — defined in Session 6.5 · Transaction Costs & Capacity (coming soon)

commodity term structure — one commodity's futures prices across expiries; its slope is net carry, set by inventories, storage and seasonality. (Session 2.5)

common random numbers — feeding every scheme or scenario being compared the same underlying random draws, so a difference in the result reflects the method, not new luck. (Session 3.5)

common stock — a share of ownership: a vote, dividends when paid, and the residual claim on whatever is left after all fixed claims, with limited liability. (Session 2.2)

compounding — returns multiplying on a growing (or shrinking) base: $\prod (1 + R_t)$. (Session 2.3)

concept drift — defined in Session 12.1 · Why Finance ML Is Different (coming soon)

condition number — $\mathrm{cond}(\Sigma) = \lambda_{\max}/\lambda_{\min}$, how far a matrix is from singular; it bounds how much inverting it can amplify relative errors. (Session 3.3)

conditional drawdown at risk — defined in Session 9.8 · Drawdowns, Copulas, Tail Risk & Stress Tests (coming soon)

conditional expectation — $\E[X \mid B]$, the average of $X$ over the outcomes in which $B$ happened — the average in a shrunken world, such as your P&L on days the signal said long. (Session 3.1)

conditional probability — the probability of A once you know B happened, $\Prob(A \mid B) = \Prob(A \cap B)/\Prob(B)$: keep only B's outcomes and rescale. (Session 3.1)

confounder — defined in Session 7.5 · Causal Factor Investing (coming soon)

conjugate prior — defined in Session 5.3 · Bayesian Thinking: Priors, Shrinkage & Updating (coming soon)

constraint — a rule every acceptable solution must satisfy, written as an equality or inequality in the decision variables. (Session 3.4)

contango — futures above spot, the curve rising with maturity; a long position pays roll yield. (Session 2.4)

continuous futures — defined in Session 4.3 · Corporate Actions, Security Master & Continuous Futures (coming soon)

contract multiplier — money per unit of the quoted price: $50 per index point for the E-mini S&P 500. (Session 2.4)

control variate — a variance-reduction technique that subtracts a quantity of known expected value, scaled to soak up the noise it shares with the estimate, leaving an estimator with the same mean and smaller variance. (Session 3.5)

convenience yield — the benefit of holding a physical commodity rather than a futures contract, inferred from prices as $y = r_f + u - \ln(F/S)/\tau$. (Session 2.5)

convex function — a function whose chord between any two points lies on or above its graph; every local minimum is global. (Session 3.4)

convex set — a set that contains the straight segment between any two of its members. (Session 3.4)

convexity — defined in Session 11.2 · Duration, Convexity & Curve PCA (coming soon)

copula — defined in Session 9.8 · Drawdowns, Copulas, Tail Risk & Stress Tests (coming soon)

corporate action — any company-initiated event that changes its shares or pays its holders: dividends, splits, spin-offs, mergers, rights issues, buybacks. (Session 2.2)

correlation — covariance divided by both standard deviations, between −1 and 1; measures only linear association, so zero correlation does not mean independence. (Session 3.1)

correlation matrix — the matrix $C$ of pairwise correlations, ones on the diagonal; $\Sigma = DCD$ with $D$ the diagonal matrix of volatilities. (Session 3.3)

cost of carry — the net cost of holding an asset to expiry: financing + storage − income − convenience yield, so $F = S e^{c\tau}$. (Session 2.4)

cost-aware optimisation — defined in Session 9.6 · Optimization with Constraints & Costs (coming soon)

counterparty risk — the risk that whoever owes you — a venue, issuer, borrower or trading partner — fails to pay. (Session 2.6)

covariance — $\Cov(X, Y) = \E[(X - \E[X])(Y - \E[Y])]$; positive when two quantities tend to land above their means together, and the cross term in the variance of a sum. (Session 3.1)

covariance denoising — defined in Session 9.2 · Covariance Estimation (coming soon)

covariance matrix — the $N \times N$ symmetric matrix $\Sigma$ with $\Sigma_{ij} = \Cov(R_i, R_j)$: variances on the diagonal, covariances off it. (Session 3.3)

covered call — owning the shares and selling a call on them: a premium now in exchange for the upside above the strike; by parity, a short put plus cash. (Session 2.7)

covered interest parity — the no-arbitrage rule $F = S\,(1 + i_q\tau)/(1 + i_b\tau)$: a deposit in one currency and a hedged deposit in the other must pay the same. (Session 2.5)

creation and redemption — authorised participants swapping the basket for new ETF shares, or ETF shares for the basket, usually in kind; the arbitrage that bounds the premium. (Session 2.2)

credible interval — defined in Session 5.3 · Bayesian Thinking: Priors, Shrinkage & Updating (coming soon)

credit default swap — defined in Session 11.4 · Credit: Spreads, CDS & Merton (coming soon)

credit spread — defined in Session 11.4 · Credit: Spreads, CDS & Merton (coming soon)

cross-currency basis — the spread $x$ added to the non-dollar interest rate that makes covered interest parity hold at market prices; negative when borrowing dollars through FX swaps costs more than in the cash market. (Session 2.5)

cross-sectional momentum — defined in Session 8.2 · Cross-Sectional Momentum & Reversal (coming soon)

cross-sectional regression — defined in Session 7.3 · Building Factors: Sorts & Fama-MacBeth (coming soon)

cross-sectional return prediction — defined in Session 12.4 · Gradient Boosting for Cross-Sectional Alpha (coming soon)

CSCV — defined in Session 6.7 · Overfitting Statistics: PSR, DSR, MinTRL & PBO (coming soon)

cumulative abnormal return — defined in Session 8.6 · Event-Driven Strategies (coming soon)

currency pair — two currencies written BASE/QUOTE; the price is how many units of the quote currency one unit of the base costs. (Session 2.5)

curve bootstrapping — defined in Session 11.1 · Yield Curves & Bootstrapping (coming soon)

custodian — a firm that holds securities on behalf of their owners, kept separate from its own assets. (Session 2.1)

custody risk — the risk of losing assets because of how and by whom they are held: hacks, lost keys, commingling or misuse. (Session 2.6)

CUSUM monitoring — defined in Session 9.9 · Performance, Attribution & When to Switch Off (coming soon)

cvxpy — an open-source Python library that checks a problem against the DCP rules, rewrites it into a solver's standard form and calls the solver. (Session 3.4)

d1 and d2 — defined in Session 10.3 · Black-Scholes-Merton (coming soon)

dark pool — a trading venue that does not display orders before they trade; in the US, a kind of alternative trading system. (Session 2.1)

data cache — a git-ignored local store of downloaded or generated data, named by its inputs and checked by a content fingerprint, so data is fetched once and reused. (Session 1.5)

data contract — defined in Session 4.6 · Lab: Build Your Research Data Lake (coming soon)

data due diligence — defined in Session 13.1 · Alternative Data (coming soon)

data exhaust — defined in Session 13.1 · Alternative Data (coming soon)

data licence — defined in Session 4.1 · The Data Landscape, Vendors & Licensing (coming soon)

data lineage — defined in Session 4.6 · Lab: Build Your Research Data Lake (coming soon)

data quality check — defined in Session 4.6 · Lab: Build Your Research Data Lake (coming soon)

data snooping — defined in Session 6.4 · The Bias Hall of Fame (coming soon)

data vendor — defined in Session 4.1 · The Data Landscape, Vendors & Licensing (coming soon)

data vintage — defined in Session 4.2 · Point-in-Time Data & Data Biases (coming soon)

dataset coverage — defined in Session 13.1 · Alternative Data (coming soon)

day count convention — defined in Session 11.1 · Yield Curves & Bootstrapping (coming soon)

decentralised exchange — a venue built from smart contracts on a public blockchain; you trade from your own wallet and trades settle on-chain. (Session 2.6)

decision variable — what an optimisation problem chooses; here, the portfolio weight vector $w$. (Session 3.4)

deflated Sharpe ratio — defined in Session 6.7 · Overfitting Statistics: PSR, DSR, MinTRL & PBO (coming soon)

delisting return — defined in Session 4.2 · Point-in-Time Data & Data Biases (coming soon)

delta — defined in Session 10.4 · The Greeks & Hedging P&L (coming soon)

delta hedging — defined in Session 10.4 · The Greeks & Hedging P&L (coming soon)

deployment — defined in Session 15.7 · Lab: Deploy a Paper-Trading Bot (coming soon)

Disciplined Convex Programming — the composition rules cvxpy uses to certify an expression convex before it will solve the problem. (Session 3.4)

discount factor — defined in Session 11.1 · Yield Curves & Bootstrapping (coming soon)

discrete monitoring — checking a barrier only at set times (daily closes, say) rather than continuously; it always understates the continuous probability of touching, which the Broadie–Glasserman–Kou correction adjusts for. (Session 3.5)

dispersion trade — defined in Session 10.7 · Trading Volatility (coming soon)

distance method — defined in Session 8.3 · Pairs Trading & Statistical Arbitrage (coming soon)

distance to default — defined in Session 11.4 · Credit: Spreads, CDS & Merton (coming soon)

diversification multiplier — defined in Session 9.5 · Sizing, Vol Targeting & Allocating Across Strategies (coming soon)

diversification ratio — the weighted-average volatility of a portfolio's holdings divided by the portfolio's own volatility; the more the holdings' risk cancels out, the higher it is. (Session 3.3)

dividend — cash paid per share to holders; the price drops by about the dividend on the ex-dividend date. (Session 2.2)

dollar bars — defined in Session 4.4 · Time, Calendars, As-of Joins & Bars (coming soon)

double descent — defined in Session 12.6 · Deep Learning, RL & the Complexity Debate (coming soon)

drawdown — the fall of wealth below its running peak; the maximum drawdown is the worst one. (Session 2.3)

drawdown duration — defined in Session 9.8 · Drawdowns, Copulas, Tail Risk & Stress Tests (coming soon)

drift detection — defined in Session 15.5 · Operations & MLOps (coming soon)

DuckDB — defined in Session 4.5 · The Research Storage Stack (coming soon)

Dupire formula — defined in Session 10.6 · Stochastic Volatility & Numerical Methods (coming soon)

duration — defined in Session 11.2 · Duration, Convexity & Curve PCA (coming soon)

DV01 — defined in Session 11.2 · Duration, Convexity & Curve PCA (coming soon)

dynamic hedge ratio — defined in Session 5.7 · Kalman Filters & Regime Models (coming soon)

early stopping — defined in Session 12.4 · Gradient Boosting for Cross-Sectional Alpha (coming soon)

earnings yield — defined in Session 8.5 · Value, Quality & Fundamental Quant (coming soon)

edge — a durable reason your trades earn more than they cost: a named counterparty who pays you, and a reason they keep paying. (Session 1.2)

effective number of independent bets — the square of the diversification ratio: the number of uncorrelated assets that would give the same risk reduction as the actual, correlated book. (Session 3.3)

effective spread — defined in Session 14.2 · Microstructure Models (coming soon)

efficient frontier — defined in Session 9.1 · Mean-Variance & Why It Breaks (coming soon)

efficient market hypothesis — defined in Session 7.1 · Efficient Markets & the Limits to Arbitrage (coming soon)

eigen-portfolio — the portfolio whose weights are one eigenvector of $\Sigma$; eigen-portfolios are mutually uncorrelated, and the $k$-th has variance equal to its eigenvalue $\lambda_k$. (Session 3.3)

eigenvalue — the factor $\lambda$ by which a matrix stretches one of its eigenvectors, $\Sigma v = \lambda v$; for a covariance matrix, the variance of the eigen-portfolio $v$. (Session 3.3)

eigenvalue clipping — repairing a non-PSD matrix by setting its negative eigenvalues to zero and rebuilding it; the result is the nearest PSD matrix in the Frobenius norm, but every clipped direction is left claiming zero risk. (Session 3.3)

eigenvector — a direction $v$ that a matrix only stretches, $\Sigma v = \lambda v$; a covariance matrix's eigenvectors are uncorrelated portfolios. (Session 3.3)

embargo — defined in Session 6.6 · Validation: Walk-Forward, Purged K-Fold & CPCV (coming soon)

empirical Bayes — defined in Session 5.3 · Bayesian Thinking: Priors, Shrinkage & Updating (coming soon)

Engle-Granger test — defined in Session 5.6 · Cointegration & Mean Reversion (coming soon)

entity masking — defined in Session 13.3 · LLMs for Return Prediction — and the Look-Ahead Trap (coming soon)

equal risk contribution — defined in Session 9.3 · Risk Parity & HRP (coming soon)

equity curve — defined in Session 6.2 · Build a Vectorized Backtester (coming soon)

equity premium — the expected return of stocks above the risk-free rate — the reward for bearing equity risk. (Session 1.2)

error maximisation — defined in Session 9.1 · Mean-Variance & Why It Breaks (coming soon)

estimation error — defined in Session 9.1 · Mean-Variance & Why It Breaks (coming soon)

ETF — an exchange-traded fund: a basket whose shares trade all day, held near its NAV by creation and redemption. (Session 2.2)

Euler-Maruyama scheme — defined in Session 10.2 · Stochastic Calculus for Engineers (coming soon)

European option — an option that can be exercised only at expiry (SPX index options, for example). (Session 2.7)

event loop — defined in Session 6.3 · Build an Event-Driven Backtester (coming soon)

event study — defined in Session 8.6 · Event-Driven Strategies (coming soon)

event-driven backtest — defined in Session 6.3 · Build an Event-Driven Backtester (coming soon)

EWMA covariance — defined in Session 9.2 · Covariance Estimation (coming soon)

EWMA crossover — defined in Session 8.1 · Time-Series Momentum & Trend Following (coming soon)

EWMA volatility — defined in Session 5.5 · Modeling Volatility (coming soon)

ex-dividend date — the first trading day on which a share trades without the right to its next dividend; under US T+1 settlement, normally the record date itself. (Session 2.2)

excess kurtosis — kurtosis minus 3, so it is zero for a normal and positive for fat tails; scipy and pandas report it by default, MATLAB does not. (Session 3.2)

excess return — return minus the risk-free rate over the same period; the part that measures skill. (Session 2.3)

exchange — a regulated venue that runs a public order book and matches its members' buy and sell orders under published rules. (Session 2.1)

exchange calendar — defined in Session 4.4 · Time, Calendars, As-of Joins & Bars (coming soon)

execution algorithm — defined in Session 14.4 · Optimal Execution & TCA (coming soon)

execution management system — defined in Session 15.1 · Architecture of a Live Trading System (coming soon)

ExecutionReport — defined in Session 15.3 · Broker APIs & FIX (coming soon)

expected shortfall — defined in Session 9.7 · VaR, ES, EVT & VaR Backtests (coming soon)

expected value — the probability-weighted average of a random variable, $\E[X] = \sum_i p_i x_i$; what a bet pays per trade in the long run. (Session 3.1)

experiment tracking — defined in Session 6.8 · Lab: The Research Protocol (coming soon)

expiry — a contract's last trading day, after which it settles in cash or by physical delivery. (Session 2.4)

exposure constraint — defined in Session 9.6 · Optimization with Constraints & Costs (coming soon)

extreme value theory — defined in Session 9.7 · VaR, ES, EVT & VaR Backtests (coming soon)

factor attribution — defined in Session 9.9 · Performance, Attribution & When to Switch Off (coming soon)

factor covariance — defined in Session 9.4 · Factor Risk Models (coming soon)

factor exposure — defined in Session 9.4 · Factor Risk Models (coming soon)

factor loading — defined in Session 7.2 · CAPM, APT & Factor Regressions (coming soon)

factor mirage — defined in Session 7.5 · Causal Factor Investing (coming soon)

factor model — defined in Session 7.2 · CAPM, APT & Factor Regressions (coming soon)

factor risk model — defined in Session 9.4 · Factor Risk Models (coming soon)

factor zoo — defined in Session 7.4 · The Factor Zoo & the Replication Debate (coming soon)

false discovery rate — defined in Session 5.2 · Regression & Inference That Doesn't Lie (coming soon)

false strategy theorem — defined in Session 6.7 · Overfitting Statistics: PSR, DSR, MinTRL & PBO (coming soon)

Fama-French factors — defined in Session 7.3 · Building Factors: Sorts & Fama-MacBeth (coming soon)

Fama-MacBeth regression — defined in Session 7.3 · Building Factors: Sorts & Fama-MacBeth (coming soon)

family-wise error rate — defined in Session 5.2 · Regression & Inference That Doesn't Lie (coming soon)

fat tails — extreme outcomes far more frequent than a normal with the same volatility allows; in returns, typically a power-law tail with an index between about 2 and 5. (Session 3.2)

fat-finger check — defined in Session 15.4 · Pre-Trade Risk & Kill Switches (coming soon)

feasible set — every choice of decision variables that satisfies every constraint; the solution is its best point. (Session 3.4)

feature stationarity — defined in Session 12.3 · Features & Sample Weights (coming soon)

Figgie — defined in Session 16.2 · Interview Drills: Probability, Mental Math & Market-Making Games (coming soon)

fill — defined in Session 6.3 · Build an Event-Driven Backtester (coming soon)

fill assumption — defined in Session 6.1 · What a Backtest Is (and Isn't) (coming soon)

fill probability — defined in Session 14.5 · Market Making (coming soon)

filtered historical simulation — defined in Session 9.7 · VaR, ES, EVT & VaR Backtests (coming soon)

finite-difference method — defined in Session 10.6 · Stochastic Volatility & Numerical Methods (coming soon)

FIX protocol — defined in Session 15.3 · Broker APIs & FIX (coming soon)

fixed-horizon label — defined in Session 12.2 · Labeling: Triple Barrier & Meta-Labeling (coming soon)

forecast — defined in Session 8.1 · Time-Series Momentum & Trend Following (coming soon)

forecast combination — defined in Session 8.7 · Combining Signals (coming soon)

forecast scaling — defined in Session 8.7 · Combining Signals (coming soon)

forward contract — a private agreement to buy or sell an asset at a fixed price on a future date; it settles once, at the end. (Session 2.4)

forward points — the forward rate minus spot, $F - S$, quoted in pips and added to spot; positive when the base currency has the lower interest rate. (Session 2.5)

forward premium puzzle — defined in Session 11.5 · FX & Macro Regimes (coming soon)

forward rate — defined in Session 11.1 · Yield Curves & Bootstrapping (coming soon)

fractional differentiation — defined in Session 12.3 · Features & Sample Weights (coming soon)

fractional Kelly — staking a fixed fraction $c \lt 1$ of the Kelly bet (half Kelly: $c = ½$); keeps $2c - c^2$ of the growth for $c$ times the volatility. (Session 3.6)

free float — the fraction of a company's shares that can actually trade, excluding blocks held by founders, families, governments or other companies. (Session 2.2)

front month — the listed contract closest to expiry, usually the most liquid. (Session 2.4)

front-running — defined in Session 15.6 · Market Conduct & Compliance (coming soon)

fundamental data — defined in Session 4.1 · The Data Landscape, Vendors & Licensing (coming soon)

fundamental law of active management — defined in Session 8.7 · Combining Signals (coming soon)

funding rate — the periodic rate longs pay shorts on a perpetual future (shorts pay when it is negative): the perp's average premium over spot, replaced by a small fixed interest rate (0.01% per 8 hours on Binance) whenever the premium is within 0.05% of it. (Session 2.6)

futures contract — a standardised, exchange-traded forward, centrally cleared and marked to market daily. (Session 2.4)

FX carry — the interest differential earned by holding a higher-rate currency funded in a lower-rate one; under CIP, the forward discount. (Session 2.5)

FX forward — an agreement today to exchange two currencies at a fixed rate on a date beyond spot; priced by covered interest parity. (Session 2.5)

FX spot — an exchange of two currencies at an agreed rate, settled on the spot date: T+2 for most pairs, T+1 for USD/CAD. (Session 2.5)

gamma — defined in Session 10.4 · The Greeks & Hedging P&L (coming soon)

gamma scalping — defined in Session 10.4 · The Greeks & Hedging P&L (coming soon)

GARCH model — defined in Session 5.5 · Modeling Volatility (coming soon)

garden leave — defined in Session 16.1 · Career Paths & the Quant Job Market (coming soon)

Garman-Klass estimator — defined in Session 5.5 · Modeling Volatility (coming soon)

generalised Pareto distribution — defined in Session 9.7 · VaR, ES, EVT & VaR Backtests (coming soon)

geometric Brownian motion — the price model whose log moves by (μ − σ²/2)Δ + σ√Δ·Z each step; simulated exactly in log space, at any step size. (Session 3.5)

GJR-GARCH model — defined in Session 5.5 · Modeling Volatility (coming soon)

Glosten-Milgrom model — defined in Session 14.2 · Microstructure Models (coming soon)

go/no-go memo — defined in Session 6.8 · Lab: The Research Protocol (coming soon)

gradient boosting — defined in Session 12.4 · Gradient Boosting for Cross-Sectional Alpha (coming soon)

grading rubric — defined in Session 16.5 · Capstone: Brief & Rubric (coming soon)

growth rate — the expected log growth of wealth per period, $g = \E[\ln(W_{t+1}/W_t)]$; typical wealth after $n$ periods is about $W_0e^{ng}$, and CAGR is $e^g - 1$ for annual $g$. (Session 3.6)

growth-inflation quadrant — defined in Session 11.5 · FX & Macro Regimes (coming soon)

HAC standard errors — defined in Session 5.2 · Regression & Inference That Doesn't Lie (coming soon)

half-life of mean reversion — defined in Session 5.6 · Cointegration & Mean Reversion (coming soon)

hazard rate — defined in Session 11.4 · Credit: Spreads, CDS & Merton (coming soon)

heartbeat — defined in Session 15.7 · Lab: Deploy a Paper-Trading Bot (coming soon)

hedge fund — a private fund for professional investors that can go long and short and use leverage; paid a management fee and a performance fee. (Session 1.1)

hedge ratio — defined in Session 5.6 · Cointegration & Mean Reversion (coming soon)

hedging P&L — defined in Session 10.4 · The Greeks & Hedging P&L (coming soon)

HERC — defined in Session 9.3 · Risk Parity & HRP (coming soon)

Heston model — defined in Session 10.6 · Stochastic Volatility & Numerical Methods (coming soon)

hidden Markov model — defined in Session 5.7 · Kalman Filters & Regime Models (coming soon)

hierarchical risk parity — defined in Session 9.3 · Risk Parity & HRP (coming soon)

high-water mark — the highest value an investor's stake has reached; performance fees are paid only on gains above it. (Session 1.1)

Hill estimator — an estimate of the tail index $\zeta$ from the $k$ largest losses, $1/\hat\zeta_k = \tfrac{1}{k}\sum_{i=1}^{k} \ln X_{(i)} - \ln X_{(k+1)}$ (Hill 1975); sensitive to the choice of $k$, the threshold. (Session 3.2)

Hill plot — the Hill estimate $\hat\zeta_k$ plotted against the threshold $k$, used to look for a stable stretch instead of trusting a single $k$. (Session 3.2)

historical simulation — defined in Session 6.1 · What a Backtest Is (and Isn't) (coming soon)

historical simulation VaR — defined in Session 9.7 · VaR, ES, EVT & VaR Backtests (coming soon)

HML — defined in Session 7.3 · Building Factors: Sorts & Fama-MacBeth (coming soon)

hot path — defined in Session 14.6 · Latency & Performance Engineering (coming soon)

Hull-White model — defined in Session 11.3 · Short-Rate Models & Swaps (coming soon)

hyperparameter search — defined in Session 12.4 · Gradient Boosting for Cross-Sectional Alpha (coming soon)

hypothesis — a falsifiable claim about why prices behave a certain way and who is on the other side. (Session 1.3)

idempotency key — defined in Session 15.3 · Broker APIs & FIX (coming soon)

idempotent pipeline — defined in Session 4.6 · Lab: Build Your Research Data Lake (coming soon)

idempotent restart — defined in Session 15.5 · Operations & MLOps (coming soon)

IID assumption — defined in Session 12.1 · Why Finance ML Is Different (coming soon)

imbalance bars — defined in Session 4.4 · Time, Calendars, As-of Joins & Bars (coming soon)

impermanent loss — a liquidity provider's shortfall against simply holding the deposit, caused by arbitrageurs trading the pool back to the market price; 2√θ/(1+θ) − 1 for a constant-product pool. (Session 2.6)

implementation shortfall — defined in Session 14.4 · Optimal Execution & TCA (coming soon)

implied volatility — the volatility that, plugged into a pricing model (usually Black-Scholes-Merton), reproduces an option's market price. (Session 2.7)

in-sample — defined in Session 6.1 · What a Backtest Is (and Isn't) (coming soon)

independence — A and B are independent when $\Prob(A \cap B) = \Prob(A)\,\Prob(B)$: knowing one tells you nothing about the other. It implies zero correlation; zero correlation does not imply it. (Session 3.1)

index — a number tracking a rule-defined basket: quantity × price summed, over a divisor adjusted so corporate actions leave the level unchanged. (Session 2.2)

index fund — a fund that holds an index's constituents at index weights, aiming to match the index rather than beat it. (Session 1.2)

index rebalance — defined in Session 8.6 · Event-Driven Strategies (coming soon)

information coefficient — defined in Session 8.7 · Combining Signals (coming soon)

information ratio — defined in Session 8.7 · Combining Signals (coming soon)

informational edge — profit from better or faster data, or better processing of it, than the price already reflects. (Session 1.2)

informed trader — defined in Session 14.2 · Microstructure Models (coming soon)

initial margin — the deposit required to open a leveraged position: dollars per contract for futures, a percentage of the position's value for stocks. (Session 2.4)

insider trading — defined in Session 15.6 · Market Conduct & Compliance (coming soon)

insurance fund — a venue's reserve, fed by liquidation fees, that absorbs losses on positions closed beyond their bankruptcy price. (Session 2.6)

interest rate swap — defined in Session 11.3 · Short-Rate Models & Swaps (coming soon)

intrinsic value — what an option would pay if exercised now: $\max(S - K, 0)$ for a call, $\max(K - S, 0)$ for a put. (Session 2.7)

inventory risk — defined in Session 14.5 · Market Making (coming soon)

inverse-volatility weighting — defined in Session 9.3 · Risk Parity & HRP (coming soon)

investor view — defined in Session 9.6 · Optimization with Constraints & Costs (coming soon)

IP assignment — defined in Session 16.1 · Career Paths & the Quant Job Market (coming soon)

Itô's lemma — defined in Session 10.2 · Stochastic Calculus for Engineers (coming soon)

Jensen's alpha — defined in Session 7.2 · CAPM, APT & Factor Regressions (coming soon)

job scheduler — defined in Session 15.7 · Lab: Deploy a Paper-Trading Bot (coming soon)

Johansen test — defined in Session 5.6 · Cointegration & Mean Reversion (coming soon)

jump-diffusion model — a constant-volatility diffusion plus rare, randomly timed jumps (a compound Poisson process); produces negative skew and fat tails from the jumps alone, unlike a GARCH market's time-varying volatility. (Session 3.2)

jupytext — a tool that stores notebooks as plain-text scripts (percent format, # %%) and keeps them in sync with .ipynb files. (Session 1.5)

Kalman filter — defined in Session 5.7 · Kalman Filters & Regime Models (coming soon)

kdb+ — defined in Session 4.5 · The Research Storage Stack (coming soon)

Kelly criterion — stake the fraction of wealth that maximises the growth rate: $f^\star = p - q/b$ for a binary bet, $(\mu - r_f)/\sigma^2$ for a continuously rebalanced position. (Session 3.6)

kernel bypass — defined in Session 14.6 · Latency & Performance Engineering (coming soon)

key rate duration — defined in Session 11.2 · Duration, Convexity & Curve PCA (coming soon)

kill criterion — a pre-agreed result that ends an idea at a gate, no arguments. (Session 1.3)

kill switch — defined in Session 15.4 · Pre-Trade Risk & Kill Switches (coming soon)

KKT conditions — primal feasibility, dual feasibility, complementary slackness and stationarity; for a convex problem, a certificate of optimality. (Session 3.4)

knowledge cutoff — defined in Session 13.3 · LLMs for Return Prediction — and the Look-Ahead Trap (coming soon)

KPSS test — defined in Session 5.4 · Stationarity & ARMA Models (coming soon)

Kupiec test — defined in Session 9.7 · VaR, ES, EVT & VaR Backtests (coming soon)

kurtosis — the standardised fourth moment $\E[(X - \mu)^4]/\sigma^4$, a measure of tail weight; 3 for a normal, so excess kurtosis is kurtosis minus 3. Its sample estimate is unreliable when tails are fat. (Session 3.2)

Kyle model — defined in Session 14.2 · Microstructure Models (coming soon)

Kyle's lambda — defined in Session 14.2 · Microstructure Models (coming soon)

Lagrange multiplier — the price attached to a constraint: how fast the optimal value improves as the constraint is loosened. (Session 3.4)

large language model — defined in Session 13.3 · LLMs for Return Prediction — and the Look-Ahead Trap (coming soon)

latency — defined in Session 14.6 · Latency & Performance Engineering (coming soon)

latency arbitrage — defined in Session 14.6 · Latency & Performance Engineering (coming soon)

latency edge — profit from acting on public information faster than others, e.g. trading against stale quotes. (Session 1.2)

law of large numbers — the average of many independent repetitions of a bet converges to its expected value; with finite variance its error shrinks like $\sigma/\sqrt n$. (Session 3.1)

law of one price — defined in Session 10.1 · No-Arbitrage & Binomial Trees (coming soon)

law of total expectation — $\E[X] = \sum_j \Prob(B_j)\,\E[X \mid B_j]$ for events $B_j$ that split the world into non-overlapping pieces: the overall average is the frequency-weighted average of the conditional ones. (Session 3.1)

layering — defined in Session 15.6 · Market Conduct & Compliance (coming soon)

lazy evaluation — defined in Session 4.5 · The Research Storage Stack (coming soon)

leakage — defined in Session 6.6 · Validation: Walk-Forward, Purged K-Fold & CPCV (coming soon)

Ledoit-Wolf shrinkage — defined in Session 9.2 · Covariance Estimation (coming soon)

level 1 data — defined in Session 4.1 · The Data Landscape, Vendors & Licensing (coming soon)

level 2 data — defined in Session 4.1 · The Data Landscape, Vendors & Licensing (coming soon)

level-slope-curvature factors — defined in Session 11.2 · Duration, Convexity & Curve PCA (coming soon)

leverage — exposure per unit of capital; multiplies excess return and volatility, and drag by its square. (Session 2.3)

leverage effect — defined in Session 5.1 · Stylized Facts of Returns (coming soon)

LightGBM — defined in Session 12.4 · Gradient Boosting for Cross-Sectional Alpha (coming soon)

likelihood — defined in Session 5.3 · Bayesian Thinking: Priors, Shrinkage & Updating (coming soon)

limit order — an order to trade only at a stated price or better: certain of its price, uncertain to execute. (Session 2.1)

limit order book — defined in Session 14.1 · The Limit Order Book (coming soon)

limits to arbitrage — defined in Session 7.1 · Efficient Markets & the Limits to Arbitrage (coming soon)

linearity of expectation — $\E[aX + bY] = a\,\E[X] + b\,\E[Y]$ for any random variables, related or not: the EV of a pile of bets is the sum of their EVs. (Session 3.1)

liquidation — the forced closing of a leveraged position by the venue or broker once its margin falls below the maintenance requirement. (Session 2.6)

liquidity premium — the return for supplying immediacy to traders who must trade now, or for holding assets that are hard to sell. (Session 1.2)

listwise deletion — keeping only the rows on which every asset has an observation before estimating a covariance matrix; always positive semi-definite, but can throw away most of the data. (Session 3.3)

LLM agent — defined in Session 13.4 · LLM Agents as Research Assistants (coming soon)

LLM look-ahead bias — defined in Session 13.3 · LLMs for Return Prediction — and the Look-Ahead Trap (coming soon)

local volatility — defined in Session 10.6 · Stochastic Volatility & Numerical Methods (coming soon)

lockfile — a generated, committed file (uv.lock) that pins the exact version and hash of every direct and indirect dependency. (Session 1.5)

log return — $r_t = \ln(1 + R_t)$; adds exactly across time. (Session 2.3)

log utility — valuing wealth by its logarithm, so a doubling is worth as much as a halving costs; the investor who maximises expected log utility bets Kelly. (Session 3.6)

lognormal distribution — the distribution of $e^X$ when $X$ is normal; positive and right-skewed, with mean above median above mode. The standard model for a price at a horizon. (Session 3.2)

long-short portfolio — defined in Session 7.3 · Building Factors: Sorts & Fama-MacBeth (coming soon)

look-ahead bias — defined in Session 4.2 · Point-in-Time Data & Data Biases (coming soon)

loss limit — defined in Session 15.4 · Pre-Trade Risk & Kill Switches (coming soon)

Loughran-McDonald dictionary — defined in Session 13.2 · Text as Data (coming soon)

macro regime — defined in Session 11.5 · FX & Macro Regimes (coming soon)

maintenance margin — the minimum equity a margin account must keep; falling below it triggers a margin call. (Session 2.4)

maker-taker fee — defined in Session 14.1 · The Limit Order Book (coming soon)

management fee — an annual fee charged as a percentage of the assets managed, paid whatever the performance. (Session 1.1)

Marchenko-Pastur distribution — defined in Session 9.2 · Covariance Estimation (coming soon)

margin call — a demand to add funds (for futures, back up to the initial margin) or have the position liquidated. (Session 2.4)

marginal variance — how fast portfolio variance grows as capital is added to one asset, $2(\Sigma w)_i$. (Session 3.4)

mark-to-market — revaluing every open position at the day's settlement price and settling the difference in cash. (Session 2.4)

market abuse regulation — defined in Session 15.6 · Market Conduct & Compliance (coming soon)

Market Access Rule — defined in Session 15.4 · Pre-Trade Risk & Kill Switches (coming soon)

market beta — defined in Session 7.2 · CAPM, APT & Factor Regressions (coming soon)

market data feed — defined in Session 15.1 · Architecture of a Live Trading System (coming soon)

market depth — defined in Session 14.1 · The Limit Order Book (coming soon)

market impact — defined in Session 6.5 · Transaction Costs & Capacity (coming soon)

market maker — a firm that continuously quotes both a bid and an ask, earning the spread and bearing inventory and adverse-selection risk. (Session 1.1)

market mode — the first principal component of a market's returns: usually all its weights share one sign, so it moves every asset together. (Session 3.3)

market order — an order to trade now at the best prices available: certain to execute in a liquid market, at an uncertain price. (Session 2.1)

market regime — defined in Session 5.7 · Kalman Filters & Regime Models (coming soon)

market-cap weighting — weighting each stock by its market value (usually float-adjusted); the one rule that needs no trading between index changes. (Session 2.2)

market-making game — defined in Session 16.2 · Interview Drills: Probability, Mental Math & Market-Making Games (coming soon)

martingale — defined in Session 10.2 · Stochastic Calculus for Engineers (coming soon)

material non-public information — defined in Session 13.1 · Alternative Data (coming soon)

maximum drawdown — defined in Session 9.8 · Drawdowns, Copulas, Tail Risk & Stress Tests (coming soon)

mean decrease accuracy — defined in Session 12.5 · Feature Importance & Interpretability (coming soon)

mean decrease impurity — defined in Session 12.5 · Feature Importance & Interpretability (coming soon)

mean-variance optimisation — defined in Session 9.1 · Mean-Variance & Why It Breaks (coming soon)

mental math — defined in Session 16.2 · Interview Drills: Probability, Mental Math & Market-Making Games (coming soon)

Merton model — defined in Session 11.4 · Credit: Spreads, CDS & Merton (coming soon)

meta-labeling — defined in Session 12.2 · Labeling: Triple Barrier & Meta-Labeling (coming soon)

mid price — halfway between the best bid and the best ask; the fair reference against which fill costs are measured. (Session 2.1)

minimum track record length — defined in Session 6.7 · Overfitting Statistics: PSR, DSR, MinTRL & PBO (coming soon)

mispricing explanation — defined in Session 7.4 · The Factor Zoo & the Replication Debate (coming soon)

model calibration — defined in Session 10.6 · Stochastic Volatility & Numerical Methods (coming soon)

model confidence set — defined in Session 5.2 · Regression & Inference That Doesn't Lie (coming soon)

model registry — defined in Session 15.5 · Operations & MLOps (coming soon)

modified duration — defined in Session 11.2 · Duration, Convexity & Curve PCA (coming soon)

moment — an average of a power of the distance from the mean, $\E[(X - \mu)^n]$; the second moment is the variance, and the third and fourth (divided by the matching power of $\sigma$) give skewness and kurtosis. (Session 3.2)

momentum crash — defined in Session 8.2 · Cross-Sectional Momentum & Reversal (coming soon)

moneyness — where the underlying's price sits relative to the strike: in, at or out of the money. (Session 2.7)

monitoring — defined in Session 15.5 · Operations & MLOps (coming soon)

Monte Carlo simulation — estimating a quantity by computing it on many random scenarios drawn from a model and averaging; the answer comes with a standard error. (Session 3.5)

Monte Carlo standard error — the standard deviation of a simulation estimate, s/√n for an average over n independent paths; report every simulated number as estimate ± 2 SE. (Session 3.5)

moving-average model — defined in Session 5.4 · Stationarity & ARMA Models (coming soon)

multiple testing — defined in Session 5.2 · Regression & Inference That Doesn't Lie (coming soon)

NautilusTrader — defined in Session 15.2 · Backtest-to-Live with NautilusTrader (coming soon)

NBBO — the national best bid and offer: the highest bid and lowest offer among US trading venues' protected quotes. (Session 2.1)

nearest correlation matrix — the closest valid correlation matrix (positive semi-definite, unit diagonal) to a broken one, found by alternating projections (Higham, 2002). (Session 3.3)

net asset value — a fund's holdings minus its liabilities, per share (NAV); what a mutual fund deals at and what an ETF's price is compared with. (Session 2.2)

Newey-West estimator — defined in Session 5.2 · Regression & Inference That Doesn't Lie (coming soon)

NewOrderSingle — defined in Session 15.3 · Broker APIs & FIX (coming soon)

no-arbitrage pricing — defined in Session 10.1 · No-Arbitrage & Binomial Trees (coming soon)

noise trader — defined in Session 7.1 · Efficient Markets & the Limits to Arbitrage (coming soon)

non-compete agreement — defined in Session 16.1 · Career Paths & the Quant Job Market (coming soon)

non-stationarity — the process generating the data changes over time (regimes, structural change, other traders adapting), so the past is an imperfect guide to the future. (Session 1.4)

normal distribution — the bell curve $N(\mu, \sigma^2)$, fixed by its mean and standard deviation; symmetric, with tails that vanish like $e^{-x^2/2}$. The limit of averages (CLT), and a poor model for single days. (Session 3.2)

notional value — price × multiplier × contracts: the exposure you carry, whatever the margin. (Session 2.4)

nowcasting — defined in Session 11.5 · FX & Macro Regimes (coming soon)

number of trials — defined in Session 6.7 · Overfitting Statistics: PSR, DSR, MinTRL & PBO (coming soon)

objective function — the single number an optimisation minimises or maximises; for minimum variance, $w^\top\Sigma w$. (Session 3.4)

OHLCV bar — defined in Session 4.1 · The Data Landscape, Vendors & Licensing (coming soon)

opening auction — defined in Session 14.1 · The Limit Order Book (coming soon)

optimal quote spread — defined in Session 14.5 · Market Making (coming soon)

option premium — the price the buyer pays the seller for an option; quoted per share, × 100 for a standard US equity contract. (Session 2.7)

oracle approximating shrinkage — defined in Session 9.2 · Covariance Estimation (coming soon)

order — defined in Session 6.3 · Build an Event-Driven Backtester (coming soon)

order management system — defined in Session 15.1 · Architecture of a Live Trading System (coming soon)

order state machine — defined in Session 15.1 · Architecture of a Live Trading System (coming soon)

ordinary least squares — defined in Session 5.2 · Regression & Inference That Doesn't Lie (coming soon)

Ornstein-Uhlenbeck process — defined in Session 5.6 · Cointegration & Mean Reversion (coming soon)

out-of-sample — data not used in any way to build or choose a strategy; spent once looked at. (Session 1.3)

overfitting — fitting the noise in a sample as if it were signal: better in-sample, worse out of sample; it grows with the number of features and trials relative to the data. (Session 1.4)

overlapping observations — defined in Session 5.2 · Regression & Inference That Doesn't Lie (coming soon)

P&L — profit and loss in currency; what you earned, scaled by position size. (Session 2.3)

p-value — defined in Session 5.2 · Regression & Inference That Doesn't Lie (coming soon)

PACF — defined in Session 5.4 · Stationarity & ARMA Models (coming soon)

pairs trading — defined in Session 8.3 · Pairs Trading & Statistical Arbitrage (coming soon)

pairwise deletion — estimating each entry of a covariance or correlation matrix from whichever observations that one pair of assets happens to share; convenient with missing data, but the resulting matrix need not be positive semi-definite. (Session 3.3)

paper account — defined in Session 15.7 · Lab: Deploy a Paper-Trading Bot (coming soon)

paper trading — running a strategy on live data with simulated money and fills. (Session 1.3)

par yield — defined in Session 11.1 · Yield Curves & Bootstrapping (coming soon)

parameter sweep — defined in Session 6.8 · Lab: The Research Protocol (coming soon)

Parkinson estimator — defined in Session 5.5 · Modeling Volatility (coming soon)

Parquet — defined in Session 4.5 · The Research Storage Stack (coming soon)

participation rate — defined in Session 14.3 · Market Impact & the Square-Root Law (coming soon)

partitioning — defined in Session 4.5 · The Research Storage Stack (coming soon)

pattern day trader rule — defined in Session 16.4 · Running Your Own Capital (coming soon)

payment for order flow — a payment from a market maker to a broker for routing it customer orders; legal with disclosure in the US, effectively banned in the UK and banned in the EU. (Session 2.1)

payoff diagram — a plot of a position's value (or P&L) at expiry against the underlying's price at expiry. (Session 2.7)

PCA residual strategy — defined in Session 8.3 · Pairs Trading & Statistical Arbitrage (coming soon)

performance attribution — defined in Session 9.9 · Performance, Attribution & When to Switch Off (coming soon)

performance fee — a share of the profits paid to the manager, usually only on gains above the high-water mark. (Session 1.1)

permanent impact — defined in Session 14.3 · Market Impact & the Square-Root Law (coming soon)

perpetual future — a futures contract with no expiry, held close to spot by periodic funding payments between longs and shorts. (Session 2.6)

pip — the conventional smallest step of an exchange rate: 0.0001 for most pairs, 0.01 for yen pairs. (Session 2.5)

point-in-time data — defined in Session 4.2 · Point-in-Time Data & Data Biases (coming soon)

point-in-time language model — defined in Session 13.3 · LLMs for Return Prediction — and the Look-Ahead Trap (coming soon)

polars — defined in Session 4.5 · The Research Storage Stack (coming soon)

portfolio manager — the person accountable for a book's P&L, who decides what to hold and how much risk to take. (Session 1.1)

portfolio sort — defined in Session 7.3 · Building Factors: Sorts & Fama-MacBeth (coming soon)

portfolio state — defined in Session 6.3 · Build an Event-Driven Backtester (coming soon)

portfolio variance — the variance of a portfolio's return, the quadratic form $w^\top \Sigma w = \sum_i \sum_j w_i w_j \Sigma_{ij}$. (Session 3.3)

position — defined in Session 6.2 · Build a Vectorized Backtester (coming soon)

position buffering — defined in Session 9.5 · Sizing, Vol Targeting & Allocating Across Strategies (coming soon)

position keeping — defined in Session 15.1 · Architecture of a Live Trading System (coming soon)

position limit — defined in Session 15.4 · Pre-Trade Risk & Kill Switches (coming soon)

position sizing — defined in Session 9.5 · Sizing, Vol Targeting & Allocating Across Strategies (coming soon)

positive definite — a positive semi-definite matrix whose eigenvalues are all strictly positive rather than merely non-negative; unlike a positive semi-definite matrix, it can be inverted. (Session 3.3)

positive semi-definite — a symmetric matrix with $w^\top \Sigma w \ge 0$ for every $w$, equivalently all eigenvalues $\ge 0$; every valid covariance matrix is one. (Session 3.3)

post-earnings-announcement drift — defined in Session 8.6 · Event-Driven Strategies (coming soon)

post-publication decay — defined in Session 7.4 · The Factor Zoo & the Replication Debate (coming soon)

posterior — defined in Session 5.3 · Bayesian Thinking: Priors, Shrinkage & Updating (coming soon)

power law — a relationship in which one quantity varies as a power of another; for a tail, $\Prob(X \gt x) \propto x^{-\zeta}$, a straight line on log–log axes and scale-free. (Session 3.2)

pre-registration — writing down the test, metrics and kill criteria before seeing results. (Session 1.3)

pre-trade risk check — defined in Session 15.4 · Pre-Trade Risk & Kill Switches (coming soon)

price collar — defined in Session 15.4 · Pre-Trade Risk & Kill Switches (coming soon)

price-time priority — defined in Session 14.1 · The Limit Order Book (coming soon)

principal component analysis — eigen-decomposing an estimated covariance or correlation matrix; the components are uncorrelated portfolios sorted by variance, the first usually the market. (Session 3.3)

prior — defined in Session 5.3 · Bayesian Thinking: Priors, Shrinkage & Updating (coming soon)

probabilistic Sharpe ratio — defined in Session 6.7 · Overfitting Statistics: PSR, DSR, MinTRL & PBO (coming soon)

probability of backtest overfitting — defined in Session 6.7 · Overfitting Statistics: PSR, DSR, MinTRL & PBO (coming soon)

probability of default — defined in Session 11.4 · Credit: Spreads, CDS & Merton (coming soon)

profiling — defined in Session 14.6 · Latency & Performance Engineering (coming soon)

profit-taking barrier — defined in Session 12.2 · Labeling: Triple Barrier & Meta-Labeling (coming soon)

profitability — defined in Session 8.5 · Value, Quality & Fundamental Quant (coming soon)

proof of reserves — an exchange's published snapshot of its wallet holdings, often with a Merkle tree of customer balances; it shows assets at one moment, not solvency. (Session 2.6)

proprietary trading firm — a firm that trades only its own capital — it manages no client money; it keeps all its P&L and bears all its losses. (Session 1.1)

protective put — owning the shares and buying a put on them: a floor under the loss, paid for with the premium; by parity, a call plus cash. (Session 2.7)

pseudo-random number generator — a deterministic function of a seed that produces a stream of numbers indistinguishable from random; the same seed and library version always give the same stream. (Session 3.5)

publication bias — defined in Session 6.4 · The Bias Hall of Fame (coming soon)

purged k-fold cross-validation — defined in Session 6.6 · Validation: Walk-Forward, Purged K-Fold & CPCV (coming soon)

purging — defined in Session 6.6 · Validation: Walk-Forward, Purged K-Fold & CPCV (coming soon)

put option — the right, not the obligation, to sell the underlying at the strike price, at or before expiry. (Session 2.7)

put-call parity — for European options, $C - P = S e^{-q\tau} - K e^{-r_f \tau}$: a call minus a put is a forward, enforced by replication. (Session 2.7)

QQ plot — sorted, standardised data plotted against the quantiles a reference distribution (usually the normal) predicts; points on the diagonal mean a match, bending ends reveal the tails. (Session 3.2)

quadratic form — an expression such as $w^\top \Sigma w$ in which every term multiplies two entries of a vector; portfolio variance is the quadratic form built from the weight vector and the covariance matrix. (Session 3.3)

quadratic program — minimising a convex quadratic objective subject to linear equality and inequality constraints. (Session 3.4)

quadratic variation — defined in Session 10.2 · Stochastic Calculus for Engineers (coming soon)

quality factor — defined in Session 8.5 · Value, Quality & Fundamental Quant (coming soon)

quant developer — builds the data, research and trading infrastructure; judged on correctness, uptime and speed. (Session 1.1)

quant researcher — finds, tests and documents predictive signals; judged on out-of-sample forecast quality and the P&L it leads to. (Session 1.1)

quant trader — turns forecasts into positions (sizing, execution, hedging); judged on P&L and risk-adjusted return. (Session 1.1)

QuantLib — defined in Session 10.6 · Stochastic Volatility & Numerical Methods (coming soon)

queue position — defined in Session 14.1 · The Limit Order Book (coming soon)

quote data — defined in Session 4.1 · The Data Landscape, Vendors & Licensing (coming soon)

random features — defined in Session 12.6 · Deep Learning, RL & the Complexity Debate (coming soon)

random matrix theory — defined in Session 9.2 · Covariance Estimation (coming soon)

random seed — the number that initialises a pseudo-random generator; the same seed on the same software gives the same stream of draws. (Session 1.5)

random variable — a number decided by chance, such as the P&L of your next trade; formally a function from outcomes to numbers, described by its distribution. (Session 3.1)

random walk — a sequence built by adding independent random steps; under GBM the log price is one. (Session 3.5)

rate limit — defined in Session 15.3 · Broker APIs & FIX (coming soon)

ratio adjustment — defined in Session 4.3 · Corporate Actions, Security Master & Continuous Futures (coming soon)

realized volatility — defined in Session 5.5 · Modeling Volatility (coming soon)

reconciliation — defined in Session 15.5 · Operations & MLOps (coming soon)

recovery rate — defined in Session 11.4 · Credit: Spreads, CDS & Merton (coming soon)

recruiting pipeline — defined in Session 16.1 · Career Paths & the Quant Job Market (coming soon)

recurrent neural network — defined in Session 12.6 · Deep Learning, RL & the Complexity Debate (coming soon)

redistribution — defined in Session 4.1 · The Data Landscape, Vendors & Licensing (coming soon)

reflection principle — pairing each path that touches a barrier and ends on one side with an equally likely (or drift-reweighted) mirror path that ends on the other, turning a path-dependent touch probability into a formula. (Session 3.5)

reinforcement learning — defined in Session 12.6 · Deep Learning, RL & the Complexity Debate (coming soon)

replicating portfolio — defined in Session 10.1 · No-Arbitrage & Binomial Trees (coming soon)

replication crisis — defined in Session 7.4 · The Factor Zoo & the Replication Debate (coming soon)

reproducibility — getting the same results again from the same data, code, environment and random seed. (Session 1.5)

research case study — defined in Session 16.3 · Stats, ML, Coding & Research-Case Interviews (coming soon)

research guardrail — defined in Session 13.4 · LLM Agents as Research Assistants (coming soon)

research log — a dated record of every trial, result and decision in a research project. (Session 1.3)

research portfolio — defined in Session 16.1 · Career Paths & the Quant Job Market (coming soon)

research report — defined in Session 16.5 · Capstone: Brief & Rubric (coming soon)

research repository — a git repository laid out for research: immutable raw data, code-derived data, notebooks, a tested package, pre-registrations and results. (Session 1.5)

reservation price — defined in Session 14.5 · Market Making (coming soon)

restatement — defined in Session 4.2 · Point-in-Time Data & Data Biases (coming soon)

rho — defined in Session 10.4 · The Greeks & Hedging P&L (coming soon)

risk contribution — defined in Session 9.3 · Risk Parity & HRP (coming soon)

risk decomposition — defined in Session 9.4 · Factor Risk Models (coming soon)

risk of ruin — the probability that wealth ever reaches a level at which you cannot or will not continue: zero, a margin call or a loss limit. (Session 3.6)

risk parity — defined in Session 9.3 · Risk Parity & HRP (coming soon)

risk premium — the extra expected return for holding a risk others want to shed; it persists because its bad times are real. (Session 1.2)

risk-based explanation — defined in Session 7.4 · The Factor Zoo & the Replication Debate (coming soon)

risk-neutral measure — defined in Session 10.1 · No-Arbitrage & Binomial Trees (coming soon)

risk-neutral pricing — defined in Session 10.3 · Black-Scholes-Merton (coming soon)

risk-neutral probability — defined in Session 10.1 · No-Arbitrage & Binomial Trees (coming soon)

Roll model — defined in Session 14.2 · Microstructure Models (coming soon)

roll schedule — defined in Session 4.3 · Corporate Actions, Security Master & Continuous Futures (coming soon)

roll yield — the return from a contract converging to spot, $(S - F)/F$ per contract, about $-c$ a year; it accrues daily, not at the roll. (Session 2.4)

roll-down — defined in Session 8.4 · Carry Across Asset Classes (coming soon)

run manifest — a record of exactly what produced a result: commit, package versions, data fingerprint and seed. (Session 1.5)

runbook — defined in Session 15.5 · Operations & MLOps (coming soon)

s-score — defined in Session 8.3 · Pairs Trading & Statistical Arbitrage (coming soon)

sample covariance — defined in Session 9.2 · Covariance Estimation (coming soon)

sample uniqueness — defined in Session 12.3 · Features & Sample Weights (coming soon)

scenario analysis — defined in Session 9.8 · Drawdowns, Copulas, Tail Risk & Stress Tests (coming soon)

security identifier — defined in Session 4.3 · Corporate Actions, Security Master & Continuous Futures (coming soon)

security master — defined in Session 4.3 · Corporate Actions, Security Master & Continuous Futures (coming soon)

selection bias — defined in Session 6.4 · The Bias Hall of Fame (coming soon)

sell side — firms that sell trading services to the buy side — execution, market making, research, financing, derivatives; mostly banks and brokers. (Session 1.1)

sentiment score — defined in Session 13.2 · Text as Data (coming soon)

sequential bootstrap — defined in Session 12.3 · Features & Sample Weights (coming soon)

settlement — the final delivery of securities against cash that completes a trade; T+1 for US equities since 28 May 2024. (Session 2.1)

settlement price — the official daily price the exchange uses to mark every futures position to market. (Session 2.4)

shadow price — a Lagrange multiplier read as a price: how much the optimal value would move if a constraint's limit moved. (Session 3.4)

SHAP values — defined in Session 12.5 · Feature Importance & Interpretability (coming soon)

Sharpe ratio — annualised mean excess return divided by its annualised volatility. (Session 2.3)

short selling — borrowing shares, selling them, and later buying them back to return; the gain is capped at 100%, the loss is not. (Session 2.2)

short squeeze — a rally that forces short sellers to buy back, whose buying pushes the price higher and forces yet more buying. (Session 2.2)

short-rate model — defined in Session 11.3 · Short-Rate Models & Swaps (coming soon)

short-term reversal — defined in Session 8.2 · Cross-Sectional Momentum & Reversal (coming soon)

shrinkage — defined in Session 5.3 · Bayesian Thinking: Priors, Shrinkage & Updating (coming soon)

signal — a number computable from data available at the time that forecasts a future return. (Session 1.3)

signal correlation — defined in Session 8.7 · Combining Signals (coming soon)

signal lag — defined in Session 6.2 · Build a Vectorized Backtester (coming soon)

signal-to-noise ratio — how much of an outcome's variation a signal explains relative to what it cannot; in daily returns even excellent signals explain well under 1% ($R^2 = \mathrm{IC}^2$). (Session 1.4)

simple return — $R_t = (P_t + D_t)/P_{t-1} - 1$; adds exactly across assets. (Session 2.3)

simulated exchange — defined in Session 15.2 · Backtest-to-Live with NautilusTrader (coming soon)

single feature importance — defined in Session 12.5 · Feature Importance & Interpretability (coming soon)

skewness — the standardised third moment $\E[(X - \mu)^3]/\sigma^3$; negative when rare large losses give a long left tail. (Session 3.2)

slippage — defined in Session 6.5 · Transaction Costs & Capacity (coming soon)

SMB — defined in Session 7.3 · Building Factors: Sorts & Fama-MacBeth (coming soon)

SOFR — defined in Session 11.3 · Short-Rate Models & Swaps (coming soon)

Sortino ratio — defined in Session 9.9 · Performance, Attribution & When to Switch Off (coming soon)

SPA test — defined in Session 5.2 · Regression & Inference That Doesn't Lie (coming soon)

specific risk — defined in Session 9.4 · Factor Risk Models (coming soon)

specification error — defined in Session 7.5 · Causal Factor Investing (coming soon)

spoofing — defined in Session 15.6 · Market Conduct & Compliance (coming soon)

spread — defined in Session 5.6 · Cointegration & Mean Reversion (coming soon)

square-root law — defined in Session 14.3 · Market Impact & the Square-Root Law (coming soon)

SSVI — defined in Session 10.5 · The Implied Volatility Surface (coming soon)

stablecoin — a token designed to hold a fixed value, usually $1, backed by fiat reserves, over-collateralised crypto, an algorithm, or a hedged crypto position (a synthetic dollar). (Session 2.6)

stale price — defined in Session 6.4 · The Bias Hall of Fame (coming soon)

standard deviation — the square root of the variance, $\sqrt{\Var(X)}$; a typical distance from the expected value, in the units of $X$. For returns it is called volatility. (Session 3.1)

standard error — the standard deviation of an estimate across repeated samples; for an average of $n$ independent draws it is $\sigma/\sqrt n$. (Session 3.1)

standard error of the Sharpe ratio — defined in Session 5.2 · Regression & Inference That Doesn't Lie (coming soon)

standardized unexpected earnings — defined in Session 8.6 · Event-Driven Strategies (coming soon)

state-space model — defined in Session 5.7 · Kalman Filters & Regime Models (coming soon)

static arbitrage — defined in Session 10.5 · The Implied Volatility Surface (coming soon)

stationarity — defined in Session 5.4 · Stationarity & ARMA Models (coming soon)

statistical arbitrage — defined in Session 8.3 · Pairs Trading & Statistical Arbitrage (coming soon)

stochastic differential equation — defined in Session 10.2 · Stochastic Calculus for Engineers (coming soon)

stock split — each share becomes N (or N become one, a reverse split); the price divides (multiplies) by N and the value is unchanged. (Session 2.2)

stop order — a dormant order that becomes a market order once the market trades at or through its stop price. (Session 2.1)

stop-loss barrier — defined in Session 12.2 · Labeling: Triple Barrier & Meta-Labeling (coming soon)

storage cost — the cost of keeping a physical commodity (rent, insurance, losses) per unit per year; it caps contango at full carry. (Session 2.5)

straddle — defined in Session 10.7 · Trading Volatility (coming soon)

strangle — defined in Session 10.7 · Trading Volatility (coming soon)

strategy allocation — defined in Session 9.5 · Sizing, Vol Targeting & Allocating Across Strategies (coming soon)

strategy engine — defined in Session 15.1 · Architecture of a Live Trading System (coming soon)

strategy retirement — defined in Session 9.9 · Performance, Attribution & When to Switch Off (coming soon)

strategy specification — defined in Session 6.1 · What a Backtest Is (and Isn't) (coming soon)

stress test — defined in Session 9.8 · Drawdowns, Copulas, Tail Risk & Stress Tests (coming soon)

strike price — the fixed price $K$ at which an option lets its holder buy (call) or sell (put). (Session 2.7)

structural break — defined in Session 5.7 · Kalman Filters & Regime Models (coming soon)

Student-t distribution — a bell-shaped distribution with degrees of freedom $\nu$ and power-law tails of index $\nu$; variance $\nu/(\nu - 2)$, so multiply by $\sqrt{(\nu - 2)/\nu}$ for unit variance. Tends to the normal as $\nu$ grows. (Session 3.2)

stylized facts — defined in Session 5.1 · Stylized Facts of Returns (coming soon)

substitution effect — defined in Session 12.5 · Feature Importance & Interpretability (coming soon)

survivorship bias — defined in Session 4.2 · Point-in-Time Data & Data Biases (coming soon)

SVI parameterisation — defined in Session 10.5 · The Implied Volatility Surface (coming soon)

swap rate — defined in Session 11.3 · Short-Rate Models & Swaps (coming soon)

swaption — defined in Session 11.3 · Short-Rate Models & Swaps (coming soon)

t-statistic — defined in Session 5.2 · Regression & Inference That Doesn't Lie (coming soon)

t-statistic hurdle — defined in Session 7.4 · The Factor Zoo & the Replication Debate (coming soon)

tail dependence — defined in Session 9.8 · Drawdowns, Copulas, Tail Risk & Stress Tests (coming soon)

tail index — the exponent $\zeta$ of a power-law tail, $\Prob(X \gt x) \approx C x^{-\zeta}$; smaller means fatter, and moments of order $\zeta$ and above are infinite. Often written $\alpha$ elsewhere. (Session 3.2)

take-home assignment — defined in Session 16.3 · Stats, ML, Coding & Research-Case Interviews (coming soon)

tangency portfolio — defined in Session 9.1 · Mean-Variance & Why It Breaks (coming soon)

target leakage — defined in Session 12.1 · Why Finance ML Is Different (coming soon)

tax lot — defined in Session 16.4 · Running Your Own Capital (coming soon)

temporary impact — defined in Session 14.3 · Market Impact & the Square-Root Law (coming soon)

text embedding — defined in Session 13.2 · Text as Data (coming soon)

TF-IDF — defined in Session 13.2 · Text as Data (coming soon)

theta — defined in Session 10.4 · The Greeks & Hedging P&L (coming soon)

tick data — defined in Session 4.1 · The Data Landscape, Vendors & Licensing (coming soon)

tick size — defined in Session 14.1 · The Limit Order Book (coming soon)

tick-to-trade latency — defined in Session 14.6 · Latency & Performance Engineering (coming soon)

time bars — defined in Session 4.4 · Time, Calendars, As-of Joins & Bars (coming soon)

time in force — the instruction that says how long an order stays live: day, good till cancelled, immediate or cancel, fill or kill, or until the close. (Session 2.1)

time value — option price minus intrinsic value: what the remaining time and uncertainty are worth (plus an interest effect). (Session 2.7)

time zone — defined in Session 4.4 · Time, Calendars, As-of Joins & Bars (coming soon)

time-decay weighting — defined in Session 12.3 · Features & Sample Weights (coming soon)

time-series momentum — defined in Session 8.1 · Time-Series Momentum & Trend Following (coming soon)

time-series regression — defined in Session 7.2 · CAPM, APT & Factor Regressions (coming soon)

timestamp — defined in Session 4.4 · Time, Calendars, As-of Joins & Bars (coming soon)

tokenisation — defined in Session 13.2 · Text as Data (coming soon)

tool use — defined in Session 13.4 · LLM Agents as Research Assistants (coming soon)

total return — price change plus dividends reinvested, $(P_t + D_t)/P_{t-1} - 1$; the return this course always means. (Session 2.2)

total-return index — defined in Session 4.3 · Corporate Actions, Security Master & Continuous Futures (coming soon)

track record — defined in Session 16.4 · Running Your Own Capital (coming soon)

trading journal — defined in Session 16.4 · Running Your Own Capital (coming soon)

trading system design interview — defined in Session 16.3 · Stats, ML, Coding & Research-Case Interviews (coming soon)

transaction cost — defined in Session 6.5 · Transaction Costs & Capacity (coming soon)

transaction cost analysis — defined in Session 14.4 · Optimal Execution & TCA (coming soon)

transformer model — defined in Session 12.6 · Deep Learning, RL & the Complexity Debate (coming soon)

trend following — defined in Session 8.1 · Time-Series Momentum & Trend Following (coming soon)

trial inflation — defined in Session 13.4 · LLM Agents as Research Assistants (coming soon)

trial log — defined in Session 6.8 · Lab: The Research Protocol (coming soon)

triple-barrier method — defined in Session 12.2 · Labeling: Triple Barrier & Meta-Labeling (coming soon)

turnover — defined in Session 6.2 · Build a Vectorized Backtester (coming soon)

turnover penalty — defined in Session 9.6 · Optimization with Constraints & Costs (coming soon)

TWAP — defined in Session 14.4 · Optimal Execution & TCA (coming soon)

uncovered interest parity — defined in Session 11.5 · FX & Macro Regimes (coming soon)

unit root — defined in Session 5.4 · Stationarity & ARMA Models (coming soon)

untradable price — defined in Session 6.4 · The Bias Hall of Fame (coming soon)

uv — a fast Python package and project manager that installs Python, creates a project's virtual environment, locks its dependencies and runs code inside it. (Session 1.5)

value at risk — defined in Session 9.7 · VaR, ES, EVT & VaR Backtests (coming soon)

value factor — defined in Session 8.5 · Value, Quality & Fundamental Quant (coming soon)

variance — the expected squared distance from the expected value, $\Var(X) = \E[(X - \E[X])^2]$; its square root, the standard deviation, is in the units of $X$. (Session 3.1)

variance reduction — any technique that lowers the variance of a Monte Carlo estimator at equal cost; measured by the variance-reduction ratio. (Session 3.5)

variance swap — defined in Session 10.7 · Trading Volatility (coming soon)

variance-reduction ratio — the variance of a plain Monte Carlo estimate divided by the variance of an improved one at equal cost; equivalently, how many times more paths the plain method would need for the same precision. (Session 3.5)

variation margin — the daily cash transfer of mark-to-market gains and losses. (Session 2.4)

Vasicek model — defined in Session 11.3 · Short-Rate Models & Swaps (coming soon)

vectorized backtest — defined in Session 6.2 · Build a Vectorized Backtester (coming soon)

vega — defined in Session 10.4 · The Greeks & Hedging P&L (coming soon)

venue adapter — defined in Session 15.2 · Backtest-to-Live with NautilusTrader (coming soon)

vertical barrier — defined in Session 12.2 · Labeling: Triple Barrier & Meta-Labeling (coming soon)

vertical spread — buying an option at one strike and selling the same type at another strike with the same expiry: cheaper than the single option, with the gain capped. (Session 2.7)

virtual environment — an isolated folder of installed packages (.venv/) that belongs to one project, so projects cannot break each other. (Session 1.5)

virtue of complexity — defined in Session 12.6 · Deep Learning, RL & the Complexity Debate (coming soon)

VIX futures — defined in Session 10.7 · Trading Volatility (coming soon)

VIX index — defined in Session 10.7 · Trading Volatility (coming soon)

volatility — the standard deviation of returns, usually annualised. (Session 2.3)

volatility clustering — defined in Session 5.1 · Stylized Facts of Returns (coming soon)

volatility drag — the gap between arithmetic mean and compound growth, ≈ σ²/2 a year. (Session 2.3)

volatility forecast — defined in Session 5.5 · Modeling Volatility (coming soon)

volatility risk premium — defined in Session 10.7 · Trading Volatility (coming soon)

volatility scaling — defined in Session 8.1 · Time-Series Momentum & Trend Following (coming soon)

volatility skew — defined in Session 10.5 · The Implied Volatility Surface (coming soon)

volatility smile — defined in Session 10.5 · The Implied Volatility Surface (coming soon)

volatility surface — defined in Session 10.5 · The Implied Volatility Surface (coming soon)

volatility targeting — defined in Session 9.5 · Sizing, Vol Targeting & Allocating Across Strategies (coming soon)

volatility term structure — defined in Session 10.5 · The Implied Volatility Surface (coming soon)

volume bars — defined in Session 4.4 · Time, Calendars, As-of Joins & Bars (coming soon)

VWAP — defined in Session 14.4 · Optimal Execution & TCA (coming soon)

walk-forward analysis — defined in Session 6.6 · Validation: Walk-Forward, Purged K-Fold & CPCV (coming soon)

wash sale rule — defined in Session 16.4 · Running Your Own Capital (coming soon)

wash trading — defined in Session 15.6 · Market Conduct & Compliance (coming soon)

weight vector — the column $w = (w_1, \dots, w_N)^\top$ of capital fractions in each asset (negative for shorts); the portfolio return is the dot product $w^\top R$. (Session 3.3)

winners minus losers — defined in Session 8.2 · Cross-Sectional Momentum & Reversal (coming soon)

XBRL — defined in Session 8.5 · Value, Quality & Fundamental Quant (coming soon)

Yang-Zhang estimator — defined in Session 5.5 · Modeling Volatility (coming soon)

yield curve — defined in Session 11.1 · Yield Curves & Bootstrapping (coming soon)

z-score — defined in Session 8.3 · Pairs Trading & Statistical Arbitrage (coming soon)

zero rate — defined in Session 11.1 · Yield Curves & Bootstrapping (coming soon)

zero-sum game — a contest where winners' gains equal losers' losses; beating the market is one among active investors, before costs. (Session 1.2)