Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

MiMIC: Multi-Modal Indian Earnings Calls Dataset to Predict Stock Prices

Sohom Ghosh, Arnab Maji, Sudip Kumar Naskar

TL;DR

The paper addresses forecasting stock price movements after earnings calls by leveraging multi-modal information from Indian companies. It introduces MiMIC, a dataset comprising earnings call transcripts, presentation slides with images and tables, fundamentals, technical indicators, and subsequent stock prices. A cascaded predictive framework integrates numeric features with text and image-derived signals, demonstrating that combining modalities improves forecast accuracy over unimodal baselines. The MiMIC dataset is released under CC-NC-SA-4.0 to promote reproducibility and further research, with future work including audio integration and intra-call price dynamics.

Abstract

Predicting stock market prices following corporate earnings calls remains a significant challenge for investors and researchers alike, requiring innovative approaches that can process diverse information sources. This study investigates the impact of corporate earnings calls on stock prices by introducing a multi-modal predictive model. We leverage textual data from earnings call transcripts, along with images and tables from accompanying presentations, to forecast stock price movements on the trading day immediately following these calls. To facilitate this research, we developed the MiMIC (Multi-Modal Indian Earnings Calls) dataset, encompassing companies representing the Nifty 50, Nifty MidCap 50, and Nifty Small 50 indices. The dataset includes earnings call transcripts, presentations, fundamentals, technical indicators, and subsequent stock prices. We present a multimodal analytical framework that integrates quantitative variables with predictive signals derived from textual and visual modalities, thereby enabling a holistic approach to feature representation and analysis. This multi-modal approach demonstrates the potential for integrating diverse information sources to enhance financial forecasting accuracy. To promote further research in computational economics, we have made the MiMIC dataset publicly available under the CC-NC-SA-4.0 licence. Our work contributes to the growing body of literature on market reactions to corporate communications and highlights the efficacy of multi-modal machine learning techniques in financial analysis.

MiMIC: Multi-Modal Indian Earnings Calls Dataset to Predict Stock Prices

TL;DR

The paper addresses forecasting stock price movements after earnings calls by leveraging multi-modal information from Indian companies. It introduces MiMIC, a dataset comprising earnings call transcripts, presentation slides with images and tables, fundamentals, technical indicators, and subsequent stock prices. A cascaded predictive framework integrates numeric features with text and image-derived signals, demonstrating that combining modalities improves forecast accuracy over unimodal baselines. The MiMIC dataset is released under CC-NC-SA-4.0 to promote reproducibility and further research, with future work including audio integration and intra-call price dynamics.

Abstract

Predicting stock market prices following corporate earnings calls remains a significant challenge for investors and researchers alike, requiring innovative approaches that can process diverse information sources. This study investigates the impact of corporate earnings calls on stock prices by introducing a multi-modal predictive model. We leverage textual data from earnings call transcripts, along with images and tables from accompanying presentations, to forecast stock price movements on the trading day immediately following these calls. To facilitate this research, we developed the MiMIC (Multi-Modal Indian Earnings Calls) dataset, encompassing companies representing the Nifty 50, Nifty MidCap 50, and Nifty Small 50 indices. The dataset includes earnings call transcripts, presentations, fundamentals, technical indicators, and subsequent stock prices. We present a multimodal analytical framework that integrates quantitative variables with predictive signals derived from textual and visual modalities, thereby enabling a holistic approach to feature representation and analysis. This multi-modal approach demonstrates the potential for integrating diverse information sources to enhance financial forecasting accuracy. To promote further research in computational economics, we have made the MiMIC dataset publicly available under the CC-NC-SA-4.0 licence. Our work contributes to the growing body of literature on market reactions to corporate communications and highlights the efficacy of multi-modal machine learning techniques in financial analysis.

Paper Structure

This paper contains 22 sections, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Problem Statement
  4. Dataset Construction
  5. Company Selection
  6. Multi-Modal Data Collection
  7. Stock Performance Data
  8. Experiments & Results
  9. Conclusion
  10. Appendix
  11. Details of Numeric Data
  12. Macroeconomic Variables:
  13. Market Data:
  14. Technical Indicators:
  15. Fundamental Indicators:
  16. ...and 7 more sections

Figures (2)

  • Figure 1: Multi-modal analysis of Earning Calls of Indian Companies
  • Figure 2: Workflow