Decision-informed Neural Networks with Large Language Model Integration for Portfolio Optimization
It addresses portfolio optimization for investors by integrating decision objectives into predictions, though it is incremental as it builds on existing LLM and decision-focused learning methods.
This paper tackles the disconnect between prediction and decision quality in portfolio optimization by integrating Large Language Models (LLMs) with decision-focused learning, showing that minimizing prediction error alone leads to suboptimal decisions. Experiments on S&P100 and DOW30 datasets demonstrate that the model consistently outperforms state-of-the-art deep learning models.
This paper addresses the critical disconnect between prediction and decision quality in portfolio optimization by integrating Large Language Models (LLMs) with decision-focused learning. We demonstrate both theoretically and empirically that minimizing the prediction error alone leads to suboptimal portfolio decisions. We aim to exploit the representational power of LLMs for investment decisions. An attention mechanism processes asset relationships, temporal dependencies, and macro variables, which are then directly integrated into a portfolio optimization layer. This enables the model to capture complex market dynamics and align predictions with the decision objectives. Extensive experiments on S\&P100 and DOW30 datasets show that our model consistently outperforms state-of-the-art deep learning models. In addition, gradient-based analyses show that our model prioritizes the assets most crucial to decision making, thus mitigating the effects of prediction errors on portfolio performance. These findings underscore the value of integrating decision objectives into predictions for more robust and context-aware portfolio management.