Measuring information in analyst reports: A machine learning approach

15 Pages Posted: 20 Sep 2021

See all articles by Charles Martineau

Charles Martineau

University of Toronto - Rotman School of Management and UTSC Management

Marius Zoican

University of Toronto at Mississauga - Department of Management; University of Toronto - Rotman School of Management

Date Written: September 16, 2021

Abstract

How to quantify the informational content of analyst reports? In this short methodological paper, we propose a measure of information contribution (IC), defined in the spirit of Shapley values. We use natural language processing to identify topics for over 90,000 analyst reports for S&P 500 stocks between January 2018 to May 2020. Next, we build the IC measure as the average cosine distance between the topic distribution for a particular report and any subset of competitor reports. A first preliminary finding is that the informational content of reports in "crowded stocks" is 41% lower than for reports in low-coverage stocks. Second, team-authored reports are 36% more informative than individual reports and women-authored reports are 12% more informative than men-authored reports.

Keywords: analyst reports, natural language processing, Shapley value, information

JEL Classification: G11, G24, G40, D83, M41

Suggested Citation

Martineau, Charles and Zoican, Marius, Measuring information in analyst reports: A machine learning approach (September 16, 2021). Rotman School of Management Working Paper No. 3925176, Available at SSRN: https://ssrn.com/abstract=3925176 or http://dx.doi.org/10.2139/ssrn.3925176

Charles Martineau

University of Toronto - Rotman School of Management and UTSC Management ( email )

105 St-George
Toronto, Ontario M5S3E6
Canada

HOME PAGE: http://charlesmartineau.com

Marius Zoican (Contact Author)

University of Toronto at Mississauga - Department of Management ( email )


Canada

University of Toronto - Rotman School of Management ( email )

105 St. George Street
Toronto, Ontario M5S 3E6 M5S1S4
Canada

HOME PAGE: http://www.mariuszoican.com

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
230
Abstract Views
872
rank
185,388
PlumX Metrics