Proceedings

TransAlpha: Lightweight Design Empowers Stock Return Forecasting

Xiao Yang

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 5209-5217.

https://doi.org/10.24963/ijcai.2026/580

Keywords

  • Machine Learning: Supervised Learning
  • Machine Learning: Deep learning architectures
  • Multidisciplinary Topics and Applications: Finance
  • Machine Learning: Applications

Abstract

In intraday stock return forecasting, existing Transformer methods face high computational complexity and do not explicitly handle noisy predictors. We propose TransAlpha, a light-weight Transformer variant tailored for cross section data to advance end-to-end forecasting methods with three novel components (Cross-Sectional Denoising for signal purification, Temporal Attention Gating for trend weighting, and Smart Pooling to avoid information loss) along with a multi-component hybrid loss function. We validate on full A-share market stock data and four key segments (CSI 300/500/1000/2000) with 400 proprietary alpha factors of 15-minute frequencies. TransAlpha outperforms state-of-the-art baselines in predictive power and portfolio profitability, indicating tailored Transformer models have significant practical value in quantitative trade.

Xiao Yang. 2026. TransAlpha: Lightweight Design Empowers Stock Return Forecasting. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 5209–5217. https://doi.org/10.24963/ijcai.2026/580
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards