Signature-Informed Transformer for Asset Allocation
This addresses the problem of objective mismatch and error amplification in deep-learning forecasters for portfolio managers, representing a novel method for a known bottleneck.
The paper tackles robust asset allocation in quantitative finance by introducing the Signature-Informed Transformer (SIT), which learns end-to-end allocation policies by directly optimizing a risk-aware financial objective, and it decisively outperforms traditional and deep-learning baselines on daily S&P 100 equity data.
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://github.com/Yoontae6719/Signature-Informed-Transformer-For-Asset-Allocation