Same Company, Same Signal: The Role of Identity in Earnings Call Transcripts

TL;DR

This paper introduces DEC, a new dataset with detailed earnings call transcripts and volatility data, revealing that current transcript models mainly reflect ticker identity rather than financial insights, and proposes simple baselines that outperform existing models.

Contribution

The paper presents DEC, a comprehensive dataset with multiple earnings records per ticker, and shows that simple, training-free baselines outperform transcript-based models in volatility prediction.

Findings

Post-earnings volatility varies significantly across tickers.

Transcript representations mainly encode ticker identity, not financial insights.

Simple baselines surpass complex transcript-based models in predicting volatility.

Abstract

Post-earnings volatility prediction is critical for investors, with previous works often leveraging earnings call transcripts under the assumption that their rich semantics contribute significantly. To further investigate how transcripts impact volatility, we introduce DEC, a dataset featuring accurate volatility calculations enabled by the previously overlooked beforeAfterMarket attribute and dense ticker coverage. Unlike established benchmarks, where each ticker has only around two earnings, DEC provides 20 earnings records per ticker. Using DEC, we reveal that post-earnings volatility undergoes significant shifts, with each ticker displaying a distinct volatility distribution. To leverage historical post-earnings volatility and capture ticker-specific patterns, we propose two training-free baselines: Post-earnings Volatility (PEV) and Same-ticker Post-earnings Volatility (STPEV). These baselines surpass all transcripts-based models on DEC as well as on established benchmarks. Additionally, we demonstrate that current transcript representations predominantly capture ticker identity rather than offering financially meaningful insights specific to each earnings. This is evidenced by two key observations: earnings representations from the same ticker exhibit significantly higher similarity compared to those from different tickers, and predictions from transcript-based models show strong correlations with prior post-earnings volatility.