Scholarlink

This study investigates the potential of replacing the Average True Range (ATR) with a predictive True Range (TR) estimate to enhance the performance of the Opening Range Breakout (ORB) trading strategy. An initial oracle based backtest demonstrates that access to future TR values significantly improves cumulative returns. Building on this insight, a Long Short-Term Memory (LSTM) neural network is employed to forecast next-day TR using a sliding window framework, focusing specifically on S&P 500 Index Futures (ES). The results indicate that incorporating the predicted TR into the ORB strategy substantially improves performance, achieving a cumulative return gain of approximately 70% relative to the ATR-based baseline. Forecasting accuracy is assessed using the Mean Absolute Percentage Error (MAPE), demonstrating consistent predictive capability. These findings provide empirical evidence that machine learning-based volatility forecasting can mitigate the lag inherent in traditional indicators, supporting more adaptive and data-driven intraday trading strategies.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Enhancing Opening Range Breakout Strategies with LSTM-Based True Range Prediction

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Mu-En Wu,
  • Sheng-Chi Luo,
  • Wei-Xi Lin,
  • Chien-Ping Chung,
  • Jun-Yo Wu,
  • Jimmy Ming-Tai Wu

摘要

This study investigates the potential of replacing the Average True Range (ATR) with a predictive True Range (TR) estimate to enhance the performance of the Opening Range Breakout (ORB) trading strategy. An initial oracle based backtest demonstrates that access to future TR values significantly improves cumulative returns. Building on this insight, a Long Short-Term Memory (LSTM) neural network is employed to forecast next-day TR using a sliding window framework, focusing specifically on S&P 500 Index Futures (ES). The results indicate that incorporating the predicted TR into the ORB strategy substantially improves performance, achieving a cumulative return gain of approximately 70% relative to the ATR-based baseline. Forecasting accuracy is assessed using the Mean Absolute Percentage Error (MAPE), demonstrating consistent predictive capability. These findings provide empirical evidence that machine learning-based volatility forecasting can mitigate the lag inherent in traditional indicators, supporting more adaptive and data-driven intraday trading strategies.