AlphaFormer: End-to-End Symbolic Regression of Alpha Factors with Transformers

Haotong Huang, Jie Peng, Zezhen Ding, Pingzhi Li, Tianlong Chen
Conference on Parsimony and Learning, PMLR 328:61-82, 2026.

Abstract

Identifying predictive patterns for stock market trends, known as alpha factors, is a critical challenge in quantitative finance. Symbolic regression (SR) methods can discover these factors as interpretable mathematical expressions, offering advantages over “black-box” machine learning approaches and manual methods that rely heavily on human expertise. However, existing SR methods typically restart the discovery process for each new dataset, failing to leverage prior knowledge. To address this limitation, we propose AlphaFormer, an encoder-decoder Transformer model designed for the end-to-end generation of synergistic alpha factors from raw stock market data. AlphaFormer leverages pre-training on synthetic datasets to efficiently uncover synergistic alpha factors for new datasets, capitalizing on acquired prior knowledge. To overcome the challenge of generating synthetic stock datasets with temporal dependencies, we introduce a novel generative framework that integrates multiple time-series generative models to generate synthetic stock data and dynamically select the highest quality samples, ensuring the creation of high-fidelity datasets crucial for pre-training. Extensive evaluations on real-world stock market datasets demonstrate that AlphaFormer outperforms existing methods across widely used metrics, achieving superior performance with significantly reduced inference computation—generating only 33% as many factors as the best baseline and requiring no further training during inference. Backtests further show that AlphaFormer delivers the highest annual return among all methods, highlighting its practical potential for superior investment performance.

Cite this Paper

BibTeX
@InProceedings{pmlr-v328-huang26a, title = {AlphaFormer: End-to-End Symbolic Regression of Alpha Factors with Transformers}, author = {Huang, Haotong and Peng, Jie and Ding, Zezhen and Li, Pingzhi and Chen, Tianlong}, booktitle = {Conference on Parsimony and Learning}, pages = {61--82}, year = {2026}, editor = {Burkholz, Rebekka and Liu, Shiwei and Ravishankar, Saiprasad and Redman, William and Huang, Wei and Su, Weijie and Zhu, Zhihui}, volume = {328}, series = {Proceedings of Machine Learning Research}, month = {23--26 Mar}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v328/main/assets/huang26a/huang26a.pdf}, url = {https://proceedings.mlr.press/v328/huang26a.html}, abstract = {Identifying predictive patterns for stock market trends, known as alpha factors, is a critical challenge in quantitative finance. Symbolic regression (SR) methods can discover these factors as interpretable mathematical expressions, offering advantages over “black-box” machine learning approaches and manual methods that rely heavily on human expertise. However, existing SR methods typically restart the discovery process for each new dataset, failing to leverage prior knowledge. To address this limitation, we propose AlphaFormer, an encoder-decoder Transformer model designed for the end-to-end generation of synergistic alpha factors from raw stock market data. AlphaFormer leverages pre-training on synthetic datasets to efficiently uncover synergistic alpha factors for new datasets, capitalizing on acquired prior knowledge. To overcome the challenge of generating synthetic stock datasets with temporal dependencies, we introduce a novel generative framework that integrates multiple time-series generative models to generate synthetic stock data and dynamically select the highest quality samples, ensuring the creation of high-fidelity datasets crucial for pre-training. Extensive evaluations on real-world stock market datasets demonstrate that AlphaFormer outperforms existing methods across widely used metrics, achieving superior performance with significantly reduced inference computation—generating only 33% as many factors as the best baseline and requiring no further training during inference. Backtests further show that AlphaFormer delivers the highest annual return among all methods, highlighting its practical potential for superior investment performance.} }
Endnote
%0 Conference Paper %T AlphaFormer: End-to-End Symbolic Regression of Alpha Factors with Transformers %A Haotong Huang %A Jie Peng %A Zezhen Ding %A Pingzhi Li %A Tianlong Chen %B Conference on Parsimony and Learning %C Proceedings of Machine Learning Research %D 2026 %E Rebekka Burkholz %E Shiwei Liu %E Saiprasad Ravishankar %E William Redman %E Wei Huang %E Weijie Su %E Zhihui Zhu %F pmlr-v328-huang26a %I PMLR %P 61--82 %U https://proceedings.mlr.press/v328/huang26a.html %V 328 %X Identifying predictive patterns for stock market trends, known as alpha factors, is a critical challenge in quantitative finance. Symbolic regression (SR) methods can discover these factors as interpretable mathematical expressions, offering advantages over “black-box” machine learning approaches and manual methods that rely heavily on human expertise. However, existing SR methods typically restart the discovery process for each new dataset, failing to leverage prior knowledge. To address this limitation, we propose AlphaFormer, an encoder-decoder Transformer model designed for the end-to-end generation of synergistic alpha factors from raw stock market data. AlphaFormer leverages pre-training on synthetic datasets to efficiently uncover synergistic alpha factors for new datasets, capitalizing on acquired prior knowledge. To overcome the challenge of generating synthetic stock datasets with temporal dependencies, we introduce a novel generative framework that integrates multiple time-series generative models to generate synthetic stock data and dynamically select the highest quality samples, ensuring the creation of high-fidelity datasets crucial for pre-training. Extensive evaluations on real-world stock market datasets demonstrate that AlphaFormer outperforms existing methods across widely used metrics, achieving superior performance with significantly reduced inference computation—generating only 33% as many factors as the best baseline and requiring no further training during inference. Backtests further show that AlphaFormer delivers the highest annual return among all methods, highlighting its practical potential for superior investment performance.
APA
Huang, H., Peng, J., Ding, Z., Li, P. & Chen, T.. (2026). AlphaFormer: End-to-End Symbolic Regression of Alpha Factors with Transformers. Conference on Parsimony and Learning, in Proceedings of Machine Learning Research 328:61-82 Available from https://proceedings.mlr.press/v328/huang26a.html.

Related Material