Backtesting SVM-Informed EUR/USD Rules with MACD and Parabolic SAR

Summary

This article turns machine-learning predictions into a rule-based EUR/USD strategy and compares its historical performance with buy and hold. Its indicators are Parabolic SAR, which trails price and reverses after a price break, and the MACD histogram, derived from the difference between the MACD and signal lines. The trading premise combines SAR direction with upward or downward MACD crossovers; the post then gives separate threshold rules for long and short positions.

The author reports testing a long-short model both with and without stop-loss and take-profit settings, using historical EUR/USD data and an R backtesting toolkit. The rule-based model is reported to have a 5.97 CAGR and 13.92 maximum drawdown, compared with 1.18 and 30.11 for buy and hold. These results are the article’s own backtest claims; it supplies no detailed validation protocol, transaction-cost analysis, sample dates, or robustness checks in the available text. The rules and parameters may need further evaluation before practical use.

Key ideas

• The strategy combines Parabolic SAR signals with MACD crossovers to define long and short trades.
• The article converts SVM output into threshold-based rules for EUR/USD.
• It compares a long-short model, a version with stop-loss and take-profit levels, and buy and hold.
• The reported backtest favors the rule-based strategy on CAGR and maximum drawdown, but the text gives limited validation details.

Tags

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