Practical introduction to statistical arbitrage, which typically refers to trading strategies that are bottom up, market neutral, with trading driven by statistical or econometric models. Models may focus on tendency of short term returns to revert, leads/lags among correlated instruments, volume momentum, or behavioral effects. A classic statistical arbitrage program is relatively high frequency over a large universe of stocks and is driven algorithmically. This course discusses a taxonomy of market participants and what motivates trading, data: different types, how to obtain data, timestamps, errors and dirty data, methods of exploring relationships between instruments, forecasting, portfolio construction across a large number of instruments, trading: the execution of portfolio changes in real markets, risks inherent in statistical arbitrage, nonstationarity of relationships due to changes in market regulations, fluctuations in market volatility and other factors, frictions such as costs of trading and constraints and how strategies scale, analysis of strategies. Prepares students with valuable skills for engaging in quantitative trading in a hedge fund or investment bank trading desk, understanding how to evaluate quantitative strategies from the point of view of an investor or asset allocator, including performance evaluation, risk analysis, and strategy capacity analysis. Occasional hands-on data projects supporting weekly topics. Weekly lectures and a final data-driven project. The objective of the final project is to build, test and analyze some kind of statistical arbitrage strategy. Prerequisites: MS&E MS&E 245A or similar, some background in probability and statistics, working knowledge of R, Python or similar computational/statistical package.
3 units · Letter or Credit/No Credit
Practical introduction to statistical arbitrage, which typically refers to trading strategies that are bottom up, market neutral, with trading driven by statistical or econometric models. Models may focus on tendency of short term returns to revert, leads/lags among correlated instruments, volume momentum, or behavioral effects. A classic statistical arbitrage program is relatively high frequency over a large universe of stocks and is driven algorithmically. This course discusses a taxonomy of market participants and what motivates trading, data: different types, how to obtain data, timestamps, errors and dirty data, methods of exploring relationships between instruments, forecasting, portfolio construction across a large number of instruments, trading: the execution of portfolio changes in real markets, risks inherent in statistical arbitrage, nonstationarity of relationships due to changes in market regulations, fluctuations in market volatility and other factors, frictions such as costs of trading and constraints and how strategies scale, analysis of strategies. Prepares students with valuable skills for engaging in quantitative trading in a hedge fund or investment bank trading desk, understanding how to evaluate quantitative strategies from the point of view of an investor or asset allocator, including performance evaluation, risk analysis, and strategy capacity analysis. Occasional hands-on data projects supporting weekly topics. Weekly lectures and a final data-driven project. The objective of the final project is to build, test and analyze some kind of statistical arbitrage strategy. Prerequisites: MS&E 245A or similar, some background in probability and statistics, working knowledge of R, Python or similar computational/statistical package.
Offered in Winter 2026 at Stanford University.