---
title: "TransAlpha: Lightweight Design Empowers Stock Return Forecasting"
authors:
  - "Xiao Yang"
doi: "10.24963/ijcai.2026/580"
url: "https://ijcai.org/proceedings/2026/580"
pdf: "https://ijcai.org/proceedings/2026/0580.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "5209-5217"
track: "Main Track"
keywords:
  - "Machine Learning: Supervised Learning"
  - "Machine Learning: Deep learning architectures"
  - "Multidisciplinary Topics and Applications: Finance"
  - "Machine Learning: Applications"
---

# TransAlpha: Lightweight Design Empowers Stock Return Forecasting

Xiao Yang

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 5209-5217. DOI: [10.24963/ijcai.2026/580](https://doi.org/10.24963/ijcai.2026/580)

## 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.