Signature-Informed Transformer for Asset Allocation

Yoontae Hwang, Stefan Zohren

Keywords: Asset Allocation, Decision Focused Learning, Forecasting

TL;DR: We introduce the Signature-Informed Transformer (SIT), a framework for robust asset allocation that embeds financial inductive biases using signatures to directly optimize a risk-aware portfolio objective.

Abstract: Robust asset allocation is a key challenge in quantitative finance, where deep-learning forecasters often fail due to objective mismatch and error amplification. We introduce the Signature-Informed Transformer (SIT), a novel framework that learns end-to-end allocation policies by directly optimizing a risk-aware financial objective. SIT's core innovations include path signatures for a rich geometric representation of asset dynamics and a signature-augmented attention mechanism embedding financial inductive biases, like lead-lag effects, into the model. Evaluated on daily S\&P 100 equity data, SIT decisively outperforms traditional and deep-learning baselines, especially when compared to predict-then-optimize models. These results indicate that portfolio-aware objectives and geometry-aware inductive biases are essential for risk-aware capital allocation in machine-learning systems. The code is available at: https://anonymous.4open.science/r/Signature-Informed-Transformer-For-Asset-Allocation-DB88

Primary Area: other topics in machine learning (i.e., none of the above)

Submission Number: 8263