Temporal Relational Reasoning of Large Language Models for Detecting Stock Portfolio Crashes

TL;DR

This paper introduces Temporal Relational Reasoning (TRR), a framework leveraging large language models to detect stock portfolio crashes by analyzing temporal, relational, and contextual information, outperforming existing methods.

Contribution

The paper presents TRR, a novel algorithmic framework that models temporal, relational, and cognitive aspects for improved crash detection in stock portfolios, extending its application to macroeconomic crises.

Findings

TRR outperforms state-of-the-art crash detection methods.

Each component of TRR significantly contributes to its performance.

TRR can be extended to macroeconomic crisis detection.

Abstract

Stock portfolios are often exposed to rare consequential events (e.g., 2007 global financial crisis, 2020 COVID-19 stock market crash), as they do not have enough historical information to learn from. Large Language Models (LLMs) now present a possible tool to tackle this problem, as they can generalize across their large corpus of training data and perform zero-shot reasoning on new events, allowing them to detect possible portfolio crash events without requiring specific training data. However, detecting portfolio crashes is a complex problem that requires more than reasoning abilities. Investors need to dynamically process the impact of each new piece of information found in news articles, analyze the relational network of impacts across different events and portfolio stocks, as well as understand the temporal context between impacts across time-steps, in order to obtain the aggregated impact on the target portfolio. In this work, we propose an algorithmic framework named Temporal Relational Reasoning (TRR). It seeks to emulate the spectrum of human cognitive capabilities used for complex problem-solving, which include brainstorming, memory, attention and reasoning. Through extensive experiments, we show that TRR is able to outperform state-of-the-art techniques on detecting stock portfolio crashes, and demonstrate how each of the proposed components help to contribute to its performance through an ablation study. Additionally, we further explore the possible applications of TRR by extending it to other related complex problems, such as the detection of possible global crisis events in Macroeconomics.