Context-Based Interpretation of Financial Information

54 Pages Posted: 4 Jan 2023 Last revised: 29 Apr 2024

See all articles by Alex Kim

Alex Kim

University of Chicago Booth School of Business

Valeri V. Nikolaev

University of Chicago Booth School of Business

Date Written: April 26, 2024

Abstract

Does the narrative context surrounding the numbers in financial statements improve the informativeness of these numbers? Answering this question empirically presents a methodological challenge. Leveraging recent advances in deep learning, we propose a method to uncover the value of interactions between numeric disclosures and their narrative context. We show that contextualization of accounting numbers makes them substantially more informative in shaping beliefs about a firm's future prospects. In fact, the informational value of interactions dominates the direct informational value of the narrative context. We corroborate this finding by showing that financial analysts incorporate the interactions between narrative and numeric information when making forecasts. Finally, we demonstrate the value of context by identifying rich firm-year-specific heterogeneity in earnings persistence.

Keywords: Earnings, cash flows, LLMs, deep learning, narrative context, earnings persistence, MD&A, neural networks, heterogeneity.

JEL Classification: G11, G12, M41

Suggested Citation

Kim, Alex G. and Nikolaev, Valeri V., Context-Based Interpretation of Financial Information (April 26, 2024). Chicago Booth Research Paper No. 23-08, Available at SSRN: https://ssrn.com/abstract=4317208 or http://dx.doi.org/10.2139/ssrn.4317208

Alex G. Kim (Contact Author)

University of Chicago Booth School of Business ( email )

5807 S. Woodlawn Avenue
Chicago, IL 60637
United States

Valeri V. Nikolaev

University of Chicago Booth School of Business ( email )

5807 South Woodlawn Avenue
Chicago, IL 60637
United States

HOME PAGE: http://faculty.chicagobooth.edu/valeri.nikolaev/index.html

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

Paper statistics

Downloads
1,232
Abstract Views
3,217
Rank
32,337
PlumX Metrics