Towards Earnings Call and Stock Price Movement

TL;DR

This paper presents a deep learning approach utilizing attention mechanisms to analyze earnings call transcripts for predicting future stock price movements, demonstrating improved accuracy over traditional methods.

Contribution

It introduces a novel deep learning model with attention for text encoding in stock prediction, highlighting the value of earnings call data.

Findings

Deep learning model outperforms traditional baselines

Earnings call information significantly improves prediction accuracy

Attention mechanism effectively captures relevant textual features

Abstract

Earnings calls are hosted by management of public companies to discuss the company's financial performance with analysts and investors. Information disclosed during an earnings call is an essential source of data for analysts and investors to make investment decisions. Thus, we leverage earnings call transcripts to predict future stock price dynamics. We propose to model the language in transcripts using a deep learning framework, where an attention mechanism is applied to encode the text data into vectors for the discriminative network classifier to predict stock price movements. Our empirical experiments show that the proposed model is superior to the traditional machine learning baselines and earnings call information can boost the stock price prediction performance.