Loading
A class of volatility models where conditional variance follows an ARMA process driven by past squared returns and past variances.
A class of volatility models where conditional variance follows an ARMA process driven by past squared returns and past variances.
Developed by Tim Bollerslev (1986) building on Robert Engle's ARCH work, GARCH(1,1) is the workhorse model for time-varying volatility. The model captures volatility clustering (periods of high and low variance), mean reversion of variance, and the fat tails observed in financial returns. It is the foundation of modern risk management and derivative pricing with stochastic volatility.
Persistence = α + β; values near 1 indicate long-memory volatility processes.
Variance targeting and mean reversion make GARCH suitable for risk forecasting.
Extensions include EGARCH (asymmetric), GJR-GARCH (leverage effect), and DCC-GARCH (multivariate).
Financial machine learning is the application of supervised, unsupervised, and reinforcement learning methods to financial prediction, classification, and decision problems. The defining methodological constraint is that financial data are serially correlated, not independently and identically distributed, which means that the standard machine learning toolkit must be substantially adapted. The dominant practitioner reference is López de Prado (2018).
Options and derivatives are financial contracts whose value derives from an underlying asset. The theory of derivative pricing, beginning with the Black-Scholes-Merton model in 1973, is the central intellectual achievement of modern quantitative finance. The practice of derivative pricing and hedging is the largest single source of employment for quants on the sell-side.