Credit Information in Earnings Calls

TL;DR

This paper introduces a new text-based method to extract credit-relevant information from earnings calls, which helps forecast future credit spread changes and firm profitability, revealing that investors underutilize this information.

Contribution

It presents a novel technique for extracting credit-related insights from earnings call transcripts that improves credit spread forecasts beyond traditional variables.

Findings

The measure predicts future credit spread risk.

The measure forecasts firm profitability.

Out-of-sample tests show investor underreaction.

Abstract

We develop a novel technique to extract credit-relevant information from the text of quarterly earnings calls. This information is not spanned by fundamental or market variables and forecasts future credit spread changes. One reason for such forecastability is that our text-based measure predicts future credit spread risk and firm profitability. More firm- and call-level complexity increase the forecasting power of our measure for spread changes. Out-of-sample portfolio tests show the information in our measure is valuable for investors. Both results suggest that investors do not fully internalize the credit-relevant information contained in earnings calls.