Learning from Earnings Calls: Graph-Based Conversational Modeling for Financial Prediction

• 成果类型: Article; Early Access
• 署名作者: Yang, Yi; Tang, Yixuan; Fan, Yangyang; Zhang, Kunpeng
• 署名单位: Hong Kong University of Science & Technology; Hong Kong Polytechnic University; University System of Maryland; University of Maryland College Park
• 刊物名称: INFORMATION SYSTEMS RESEARCH
• ISSN/ISSBN: 1047-7047; 1526-5536
• DOI: 10.1287/isre.2023.0519
• 发表日期: 2026-01-16
• 关键词: conversation modeling; conversation graph; earnings conference calls; graph neural network; financial prediction; Textual analysis; INFORMATION; volatility; cost; disclosure; anomalies; forecasts; analysts

摘要

Earnings conference calls are valuable venues for business communication. Empirical research shows that the content of earnings calls contains predictive signals about future market risks, and this has motivated a line of computational studies that utilize earnings transcripts for financial forecasting tasks. However, earnings call transcripts are typically very long, and the predictive signals within them are often sparsely distributed across different sections of the transcript. As a result, existing computational methods often fail to capture the essential information within the transcript that is relevant to market risks. In this work, we design a novel method to model earnings transcripts as a conversational graph on which graph nodes represent discussed topics and graph edges indicate the similarity between topics. By doing so, we aim to explicitly model what is discussed (i.e., topical content), how it is discussed (e.g., cross-referencing or newly introduced topics), and in what manner it is discussed (e.g., sentiment and other linguistic features) within the transcript. We then leverage a graph neural network to learn transcript-level representations for financial risk forecasting. Experimental results show that the proposed method significantly reduces risk forecasting errors, demonstrating its capability of modeling earnings call transcripts. Moreover, this predictive power holds even after considering the firm's fundamentals, and the performance gain over baseline models continues to grow as transcript length increases. The interpretability analysis shows that the proposed method identifies cross-referencing and newly introduced topics as influential for risk prediction. Moreover, the model tends to associate transcripts with a higher number of new topics in the question-and-answer section, more cross-referencing discussions, and more positive sentiment with lower predicted financial risks. This work contributes methodologically by proposing a novel predictive approach specifically tailored to the domain-specific challenge of transcript-based risk forecasting. We also discuss key design insights and implications.