Quant Methods
Systematic investing runs on statistics, and this category covers the toolkit.
The explainers work through volatility modeling with GARCH and stochastic volatility, regime-switching and hidden Markov models, copulas, extreme value theory, and cointegration for pairs and relative value, then the Kalman filter, the Hurst exponent, and price-impact measures like Kyle's lambda.
Every technique is tied to a job: what it estimates, when it helps, and where it quietly breaks down.
These methods sit under modern risk systems and signal research alike.
Investing With Purpose keeps the math purposeful rather than ornamental, so you finish understanding the models that drive the quantitative side of markets, not just their names.
The Amihud illiquidity measure, known as ILLIQ, estimates how much a stock's price moves per dollar of trading. A…
Transaction Cost Analysis (TCA) measures the real cost of executing trades and compares it to benchmarks. Good TCA…
A **prime broker** is a large bank or broker-dealer that sits at the center of a hedge fund's operations. It provides…
GARCH is a time-series model that treats a market's variance as a process with memory. It captures the empirical fact…
Stochastic volatility models treat volatility itself as a random process driven by its own source of randomness, not as…
Regime-switching models assume that the parameters governing a time series change discretely between a small number of…
A copula is a mathematical function that couples the marginal distributions of several random variables into a joint…
Extreme Value Theory is the branch of statistics that deals with the tails of distributions rather than their middles.…
Cointegration is the property that two or more non-stationary time series can share a long-run equilibrium even though…
The Kalman filter is a recursive algorithm that estimates the hidden state of a linear dynamic system from a stream of…
A Hidden Markov Model (HMM) is a probabilistic framework for time series where an unobserved state follows a Markov…
The Hurst exponent is a single number that summarizes the long-range dependence of a time series. It classifies a…
Kyle's lambda is the slope that links signed order flow to price changes. A higher lambda means each unit of buying or…
A market impact model predicts how much a trade will move the price against itself. Two canonical frameworks dominate:…
Execution algorithms break a parent order into many child orders and send them to the market according to a rule. The…
Implementation shortfall (IS) measures the gap between the return of a paper portfolio, executed at the price when the…
Slippage is the difference between the price you expected and the price you got. A slippage model predicts that…
Volatility clustering is the empirical observation that large price moves tend to be followed by more large moves, and…
Fat tails describe a return distribution where extreme outcomes occur far more often than a normal distribution would…
Skewness measures how asymmetric a return distribution is. Negative skew means the left tail is longer or heavier than…
Serial correlation, also called autocorrelation, measures how today's return relates to returns from previous periods.…
Maximum likelihood estimation is a general method for fitting a statistical model by choosing parameters that make the…
Bayesian inference combines a prior belief about unknown quantities with observed data to produce an updated, posterior…
Ensemble methods combine predictions from many models into a single, more reliable output. In finance, they are the…
Feature engineering is the process of turning raw market, fundamental, and alternative data into inputs that a…
VWAP and TWAP are two of the oldest scheduled execution algorithms used by institutional traders to break a large order…
An implementation shortfall (IS) algorithm tries to minimize the gap between the price at the moment the decision was…
A Percent of Volume (POV) algorithm, also called a participation algorithm, executes a parent order as a fixed fraction…
Sniper and liquidity-seeking algorithms are opportunistic execution engines that hunt displayed and hidden size across…
Dark pool routing is the set of rules an execution system uses to decide which off-exchange venues to send child orders…
A smart order router (SOR) is the execution-layer engine that decides which venues to send each child order to, in…
Transaction cost analysis is the measurement discipline that compares the price a trader actually paid against a set of…
The Almgren-Chriss model is the benchmark mathematical framework for optimal trade execution. Published in 2000 in the…