Leveraging Text Mining to Extract Insights From Earnings Call Transcripts

24 May 2023

2 min read

What You Need to Know

In research contributed to the Journal Investment Management, AB’s data science experts test the efficacy of text mining techniques and find that there are opportunities to use these signals in stock selection.

Download PDF

Andrew Y. Chin| Chief Artificial Intelligence Officer

Yuyu Fan| Principal Data Scientist—Investment Solutions and Sciences

Introduction

We apply text-mining techniques in earnings call transcripts to extract meaningful features that capture management and investment community signals.

Using a corpus of transcripts of earnings calls for global companies from 2010 to 2021, we create fundamentally-driven features spanning document attributes, readability and sentiment on different sections of the transcripts. We test the efficacy of these features in predicting the future stock returns of companies and find opportunities for investors to use these signals in stock selection. Specifically, we find that readability- and sentiment-based techniques can enhance an investor’s ability to differentiate among outperformers and underperformers, results that are robust across market capitalizations as well as investment universes (US large cap, US small cap, world ex-US and emerging markets).

We also introduce methods to create more robust sentiment features for active and systematic investors. By analyzing the performance patterns of the various call participants, we find evidence that analyst questions may contain more information than the executive sections. Finally, we observe that sentiment features derived from context-driven deep-learning language models like BERT are promising and may have more efficacy than bag-of-words approaches.

Past performance, historical and current analyses, and expectations do not guarantee future results.

The views expressed herein do not constitute research, investment advice or trade recommendations and do not necessarily represent the views of all AB portfolio-management teams. Views are subject to revision over time.

About the Authors

Andrew Y. Chin

Andrew Chin is Chief Artificial Intelligence (AI) Officer and a member of the firm’s Operating Committee. In this role, he leads the firm’s strategy to leverage AI in transforming the organization and driving better outcomes for clients and the firm. Previously, Chin was the Head of Investment Solutions and Sciences, overseeing the research, management and strategic growth of the firm’s asset-allocation, data science, index and tax-management businesses. From 2022 to 2023, he was the head of Quantitative Research and chief data scientist, developing and optimizing quantitative research and data science infrastructure, capabilities and resources across the organization. As the firm’s chief risk officer from 2009 to 2021, Chin led all aspects of risk management and built a global team to identify, manage and mitigate the various risks across the organization. He has held various leadership roles in quantitative research, risk management and portfolio management in New York and London since joining the firm in 1997. Before joining AB, Chin spent three years as a project manager and business analyst in global investment management at Bankers Trust. He holds a BA in math and computer science, and an MBA in finance from Cornell University. Location: New York

Yuyu Fan

Yuyu Fan is a Principal Data Scientist on the Investment Solutions and Sciences team. In this role, she leverages statistical, machine-learning and deep-learning models to draw insights from financial data. Prior to joining AB in 2018, Fan worked at College Board as a psychometrician intern, using machine-learning models to monitor test validity, reliability and security. She holds a BA in sociology from Zhejiang University (Hangzhou, China), MAs in sociology and psychology from Fordham University, and a PhD in psychometrics and quantitative psychology from Fordham University. Location: New York

This information is for exclusive use of the wholesale person to whom it is provided and is not to be relied upon by any other person. It is not intended for retail or public use and may not be further distributed without prior written consent of ABAL.
This webpage has been prepared by AllianceBernstein Australia Limited (“ABAL”)—ABN 53 095 022 718, AFSL 230 698. Information in this webpage is only intended for persons that qualify as “wholesale clients,” as defined by the Financial Markets Conduct Act 2013’, and is not to be construed as advice. This webpage is provided solely for informational purposes and is not an offer to buy or sell securities. The information, forecasts and opinions set forth in this webpage have not been prepared for any recipient’s specific investment objectives, financial situation or particular needs. Neither this webpage nor the information contained in it are intended to take the place of professional advice.
You should not take action on specific issues based on the information contained in this webpage without first obtaining professional advice. Past performance does not guarantee future results. Projections, although based on current information, may not be realized. Information, forecasts and opinions can change without notice and ABAL does not guarantee the accuracy of the information at any particular time. Although care has been exercised in compiling the information contained in this webpage, ABAL does not warrant that this webpage is free from errors, inaccuracies or omissions. ABAL disclaims any liability for damage or loss arising from reliance upon any matter contained in this webpage except for statutory liability which cannot be excluded.
No reproduction of the materials on this webpage may be made without the express written permission of ABAL. This information is provided for persons in Australia only and is not being provided for the use of any person who is in any other country.

Leveraging Text Mining to Extract Insights From Earnings Call Transcripts

What You Need to Know

Introduction

More For You