Trading Under Uncertainty: A Distribution-Based Strategy for Futures Markets Using FutureQuant Transformer

TL;DR

The paper tackles the challenge of forecasting futures prices under high uncertainty and high-frequency data by proposing the FutureQuant Transformer, a distribution-based model that predicts price quantiles through attention mechanisms. It shifts from point forecasts to probabilistic forecasts, enabling more robust risk assessment and decision making, and demonstrates its value by achieving a Prediction Interval Coverage Probability of $0.962$ with a tight interval width ($\text{CWC}=3.175$). The approach is coupled with a trading strategy that leverages RSI, Bollinger Bands, and ATR, yielding improved short-term performance and controlled risk, including an average trade gain of $0.1193\%$ per 30 minutes. Empirical results show the FutureQuant Transformer outperforming quantile-LSTM baselines in both interval accuracy and market-tracking capability, and the paper outlines future directions for generalizing to multiple futures and integrating with automated trading systems.

Abstract

In the complex landscape of traditional futures trading, where vast data and variables like real-time Limit Order Books (LOB) complicate price predictions, we introduce the FutureQuant Transformer model, leveraging attention mechanisms to navigate these challenges. Unlike conventional models focused on point predictions, the FutureQuant model excels in forecasting the range and volatility of future prices, thus offering richer insights for trading strategies. Its ability to parse and learn from intricate market patterns allows for enhanced decision-making, significantly improving risk management and achieving a notable average gain of 0.1193% per 30-minute trade over state-of-the-art models with a simple algorithm using factors such as RSI, ATR, and Bollinger Bands. This innovation marks a substantial leap forward in predictive analytics within the volatile domain of futures trading.

Figures (8)

• Figure 1: basic structure of the Quartile Transformer
• Figure 2: Quantile Attention LSTM with Predicting Interval
• Figure 3: FutureQuant with Predicting Interval
• Figure 4: Combine Past Observations with Prediction Intervals (Attention-LSTM VS FutureQuant)
• Figure 5: Cumulative return of Quantile-Attention LSTM