Distilling Analysis from Generative Models for Investment Decisions

TL;DR

This paper introduces a new dataset and a Chain-of-Decision approach to better model and predict financial professionals' decision-making processes, especially in trading, by incorporating subjective analysis from news items.

Contribution

The paper presents a novel dataset A3 and a Chain-of-Decision method that improves modeling of professional decisions in finance through opinion generation and analysis.

Findings

Current models struggle with forecasting professional behaviors.

The Chain-of-Decision approach shows promising performance improvements.

Incorporating subjective news analysis enhances decision modeling.

Abstract

Professionals' decisions are the focus of every field. For example, politicians' decisions will influence the future of the country, and stock analysts' decisions will impact the market. Recognizing the influential role of professionals' perspectives, inclinations, and actions in shaping decision-making processes and future trends across multiple fields, we propose three tasks for modeling these decisions in the financial market. To facilitate this, we introduce a novel dataset, A3, designed to simulate professionals' decision-making processes. While we find current models present challenges in forecasting professionals' behaviors, particularly in making trading decisions, the proposed Chain-of-Decision approach demonstrates promising improvements. It integrates an opinion-generator-in-the-loop to provide subjective analysis based on each news item, further enhancing the proposed tasks' performance.