pair-trade-screener

To find cointegrated stock pairs for mean-reversion trading, you can screen stocks by sector or custom symbol lists and apply statistical tests to rank pairs based on correlation, hedge ratio, and cointegration p-value.

Cointegration testing identifies mean-reverting spreads by applying the ADF test to confirm a stationary relationship between paired stocks, calculating half-life and z-score metrics to signal entry and exit points.

Yes, pair screening requires Python with pandas, numpy, scipy, and statsmodels to calculate hedge ratios, perform ADF cointegration tests, and estimate half-life for mean-reversion analysis.

Yes, you can screen custom stock symbol lists instead of sector-based screening, receiving a ranked JSON results file and console summary of cointegrated pairs with metrics like z-score and half-life.

The best way to rank cointegrated pairs by half-life and z-score is to run a sector screen or custom list, outputting a JSON report that sorts pairs based on statistical significance and current spread metrics.

Pair screening requires historical price data from the FMP API to calculate correlation, compute hedge ratios, and run ADF cointegration tests necessary for identifying statistically significant mean-reversion opportunities.