Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

From Votes to Volatility Predicting the Stock Market on Election Day

Igor L. R. Azevedo, Toyotaro Suzumura

TL;DR

This work tackles the problem of forecasting stock market behavior on Election Day, a period of heightened volatility driven by policy uncertainty. It introduces the Election Day Stock Market Forecasting (EDSMF) model, which extends the StockMixer architecture by integrating political signals generated via a dedicated LLM-agent framework and by encoding candidate-specific contexts through ensemble strategies. The method targets 1-minute, high-frequency predictions around the 2024 US presidential election, and the authors report improvements in Information Coefficient, Rank Information Coefficient, Precision@N, and Sharpe Ratio compared with baselines. The study demonstrates the practical value of combining political-awareness with advanced forecasting, offering a pathway for more scenario-specific investment insights and suggesting future work on broader political and macroeconomic signals.

Abstract

Stock market forecasting has been a topic of extensive research, aiming to provide investors with optimal stock recommendations for higher returns. In recent years, this field has gained even more attention due to the widespread adoption of deep learning models. While these models have achieved impressive accuracy in predicting stock behavior, tailoring them to specific scenarios has become increasingly important. Election Day represents one such critical scenario, characterized by intensified market volatility, as the winning candidate's policies significantly impact various economic sectors and companies. To address this challenge, we propose the Election Day Stock Market Forecasting (EDSMF) Model. Our approach leverages the contextual capabilities of large language models alongside specialized agents designed to analyze the political and economic consequences of elections. By building on a state-of-the-art architecture, we demonstrate that EDSMF improves the predictive performance of the S&P 500 during this uniquely volatile day.

From Votes to Volatility Predicting the Stock Market on Election Day

TL;DR

This work tackles the problem of forecasting stock market behavior on Election Day, a period of heightened volatility driven by policy uncertainty. It introduces the Election Day Stock Market Forecasting (EDSMF) model, which extends the StockMixer architecture by integrating political signals generated via a dedicated LLM-agent framework and by encoding candidate-specific contexts through ensemble strategies. The method targets 1-minute, high-frequency predictions around the 2024 US presidential election, and the authors report improvements in Information Coefficient, Rank Information Coefficient, Precision@N, and Sharpe Ratio compared with baselines. The study demonstrates the practical value of combining political-awareness with advanced forecasting, offering a pathway for more scenario-specific investment insights and suggesting future work on broader political and macroeconomic signals.

Abstract

Stock market forecasting has been a topic of extensive research, aiming to provide investors with optimal stock recommendations for higher returns. In recent years, this field has gained even more attention due to the widespread adoption of deep learning models. While these models have achieved impressive accuracy in predicting stock behavior, tailoring them to specific scenarios has become increasingly important. Election Day represents one such critical scenario, characterized by intensified market volatility, as the winning candidate's policies significantly impact various economic sectors and companies. To address this challenge, we propose the Election Day Stock Market Forecasting (EDSMF) Model. Our approach leverages the contextual capabilities of large language models alongside specialized agents designed to analyze the political and economic consequences of elections. By building on a state-of-the-art architecture, we demonstrate that EDSMF improves the predictive performance of the S&P 500 during this uniquely volatile day.

Paper Structure

This paper contains 29 sections, 11 equations, 1 figure, 2 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Election Day and The Stock Market
  3. Stock Market Forecasting
  4. Stock Market Forecasting on Election Day
  5. Methodology
  6. Overall Setting
  7. Problem Definition
  8. Input Features
  9. Extending StockMixer with Political Signals
  10. Candidate Impact
  11. LLM-Agent Framework for Political Signal Generation
  12. Formulation
  13. Candidate Context
  14. Random Assignment Strategy
  15. Ensemble Strategy
  16. ...and 14 more sections

Figures (1)

  • Figure 1: Comparison of performance metrics ('Prec@10', 'IC', 'RIC', 'SR') for various ensemble configurations. Each bar chart represents a single metric, highlighting the contribution of different weights assigned to candidates 1 and 2. Models are labeled as 'weight1-weight2', where 'weight1' represents the percentage for candidate 1, and 'weight2' represents the percentage for candidate 2.