Cointegration-Based Pairs Trading in INR Currency Pairs

Summary

This project describes a daily statistical arbitrage strategy applied to six INR currency pairs over the stated 2011–2013 sample. It screens pair combinations with cointegration tests, then applies a cointegrated Augmented Dickey–Fuller test to selected pairs to assess whether a linear combination of their prices is stationary. The report uses a 30-day moving average and standard deviation to calculate ratio z-scores. It enters short when the score reaches +2 and exits at +1, or enters long at −2 and exits at −1, while holding at most one position at a time.

The author reports a backtest ending equity of INR 114.05 from INR 100 initial capital, alongside trade counts, hit ratio, and maximum drawdown; a leveraged return is also presented. These are historical results from the specified sample, not evidence of future performance. The model omits slippage, commissions, and bid–ask spreads, and the document gives limited detail on position sizing and robustness testing. Its reported results therefore may overstate implementable returns.

Key ideas

• The project screens INR currency pairs for cointegration before selecting pairs for strategy testing.
• A CADF test estimates a hedge relationship and tests whether the resulting spread is stationary.
• The strategy trades price-ratio z-score reversions using stated entry and exit thresholds.
• The reported backtest excludes slippage, commissions, and bid–ask spreads.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.