Loading
A statistical property where a linear combination of two non-stationary price series forms a stationary, mean-reverting series.
A statistical property where a linear combination of two non-stationary price series forms a stationary, mean-reverting series.
Cointegration tests whether two asset prices share a long-term equilibrium relationship, despite individual non-stationary price wandering. Used extensively in pairs trading and Statistical Arbitrage.
Engle-Granger and Johansen tests verify cointegration.
Superior to simple correlation for pairs trading because correlation does not guarantee bound spreads.
Algorithmic trading is the use of computer programs to automate order generation, submission, and execution in financial markets. It spans systematic strategies (where the algorithm decides what to trade), execution algorithms (where the algorithm decides how to trade an existing decision), and high-frequency market-making. The defining feature is that a machine not a human produces and manages the orders.
Quantitative research is the disciplined process of turning a financial hypothesis into a validated, deployable trading model. It spans data engineering, signal design, backtesting with proper out-of-sample validation, and ongoing production monitoring. The discipline's central problem is overfitting: most strategies that pass backtests fail in production.