A Learnable Wavelet Transformer for Long-Short Equity Trading and Risk-Adjusted Return Optimization

2026-01-19

AI Summary

This study addresses the challenges of learning intraday long-short trading strategies from financial time series, which are characterized by high noise levels, non-stationarity, and cross-sectional dependencies among assets. To tackle these issues, the authors propose WaveLSFormer, an end-to-end architecture that integrates a learnable wavelet front-end with a Transformer backbone. The model employs a learnable wavelet filter bank for multi-scale decomposition and introduces a low-frequency-guided high-frequency injection mechanism to enhance cross-scale information fusion. Furthermore, it incorporates spectral regularization and risk-aware regularization to directly optimize risk-adjusted returns. Evaluated on five years of hourly data across six sectors, WaveLSFormer significantly outperforms baseline models—including MLP, LSTM, and standard Transformer—achieving an average cumulative return of 0.607 ± 0.045 and a Sharpe ratio of 2.157 ± 0.166.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Natural Language Processing: Learning & Optimization for NLP
• Multiagent Systems: Multiagent Learning

Application Category

• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Learning profitable intraday trading policies from financial time series is challenging due to heavy noise, non-stationarity, and strong cross-sectional dependence among related assets. We propose \emph{WaveLSFormer}, a learnable wavelet-based long-short Transformer that jointly performs multi-scale decomposition and return-oriented decision learning. Specifically, a learnable wavelet front-end generates low-/high-frequency components via an end-to-end trained filter bank, guided by spectral regularizers that encourage stable and well-separated frequency bands. To fuse multi-scale information, we introduce a low-guided high-frequency injection (LGHI) module that refines low-frequency representations with high-frequency cues while controlling training stability. The model outputs a portfolio of long/short positions that is rescaled to satisfy a fixed risk budget and is optimized directly with a trading objective and risk-aware regularization. Extensive experiments on five years of hourly data across six industry groups, evaluated over ten random seeds, demonstrate that WaveLSFormer consistently outperforms MLP, LSTM and Transformer backbones, with and without fixed discrete wavelet front-ends. On average in all industries, WaveLSFormer achieves a cumulative overall strategy return of $0.607 \pm 0.045$ and a Sharpe ratio of $2.157 \pm 0.166$, substantially improving both profitability and risk-adjusted returns over the strongest baselines.

Problem

• intraday trading
• financial time series
• non-stationarity
• cross-sectional dependence
• risk-adjusted return

Innovation

• learnable wavelet
• multi-scale decomposition
• risk-adjusted return
• low-guided high-frequency injection
• long-short equity trading