https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4835311 Skip to main content PDF iconDownload This Paper Open PDF in Browser Add Paper to My Library Share: * * * * Permalink Using these links will ensure access to this page indefinitely [https://papers.ssrn.] Copy URL [https://dx.doi.org/1] Copy DOI Financial Statement Analysis with Large Language Models Chicago Booth Research Paper Forthcoming Fama-Miller Working Paper 54 Pages Posted: 21 May 2024 See all articles by Alex Kim Alex Kim University of Chicago Booth School of Business Maximilian Muhn University of Chicago - Booth School of Business Valeri V. Nikolaev University of Chicago Booth School of Business Date Written: May 20, 2024 Abstract We investigate whether an LLM can successfully perform financial statement analysis in a way similar to a professional human analyst. We provide standardized and anonymous financial statements to GPT4 and instruct the model to analyze them to determine the direction of future earnings. Even without any narrative or industry-specific information, the LLM outperforms financial analysts in its ability to predict earnings changes. The LLM exhibits a relative advantage over human analysts in situations when the analysts tend to struggle. Furthermore, we find that the prediction accuracy of the LLM is on par with the performance of a narrowly trained state-of-the-art ML model. LLM prediction does not stem from its training memory. Instead, we find that the LLM generates useful narrative insights about a company's future performance. Lastly, our trading strategies based on GPT's predictions yield a higher Sharpe ratio and alphas than strategies based on other models. Taken together, our results suggest that LLMs may take a central role in decision-making. Keywords: GPT4, neural network, asset pricing, earnings, direction of earnings changes, analysts, chain-of-thought, financial statement analysis, large language models JEL Classification: G12, G14, G41, M41 Suggested Citation: Suggested Citation Kim, Alex G. and Muhn, Maximilian and Nikolaev, Valeri V., Financial Statement Analysis with Large Language Models (May 20, 2024). Chicago Booth Research Paper Forthcoming, Fama-Miller Working Paper, Available at SSRN: https://ssrn.com/abstract=4835311 or http:// dx.doi.org/10.2139/ssrn.4835311 Alex G. Kim (Contact Author) University of Chicago Booth School of Business University of Chicago Booth School of Business ( email ) 5807 S. Woodlawn Avenue Chicago, IL 60637 United States Maximilian Muhn University of Chicago - Booth School of Business 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 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 PDF iconDownload This Paper Open PDF in Browser Do you have a job opening that you would like to promote on SSRN? Place Job Opening Paper statistics Downloads 20,504 Abstract Views 76,980 Rank 623 PlumX Metrics Related eJournals * Financial Accounting eJournal Follow Financial Accounting eJournal Subscribe to this fee journal for more curated articles on this topic FOLLOWERS 3,559 PAPERS 18,694 This Journal is curated by: Anne Beyer at Stanford Graduate School of Business * Capital Markets: Asset Pricing & Valuation eJournal Follow Capital Markets: Asset Pricing & Valuation eJournal Subscribe to this fee journal for more curated articles on this topic FOLLOWERS 3,024 PAPERS 32,573 * Applied Accounting - Practitioner eJournal Follow Applied Accounting - Practitioner eJournal Subscribe to this fee journal for more curated articles on this topic FOLLOWERS 988 PAPERS 2,859 * Accounting Technology & Information Systems eJournal Follow Accounting Technology & Information Systems eJournal Subscribe to this fee journal for more curated articles on this topic FOLLOWERS 900 PAPERS 1,348 This Journal is curated by: Vernon J. Richardson at University of Arkansas at Fayetteville * Accounting - Disclosure eJournal Follow Accounting - Disclosure eJournal Subscribe to this free journal for more curated articles on this topic FOLLOWERS 490 PAPERS 151 This Journal is curated by: Ed deHaan at Affiliation not provided to SSRN * Investments eJournal Follow Investments eJournal Subscribe to this fee journal for more curated articles on this topic FOLLOWERS 243 PAPERS 5,783 * Generative AI eJournal Follow Generative AI eJournal Subscribe to this free journal for more curated articles on this topic FOLLOWERS 226 PAPERS 544 * Chicago Booth Research Network Papers Follow Chicago Booth Research Network Papers Subscribe to this free journal for more curated articles on this topic FOLLOWERS 50 PAPERS 489 Feedback Feedback to SSRN Feedback (required) [ ] Email (required) [ ] Submit If you need immediate assistance, call 877-SSRNHelp (877 777 6435) in the United States, or +1 212 448 2500 outside of the United States, 8:30AM to 6:00PM U.S. Eastern, Monday - Friday. Submit a Paper Section 508 Text Only Pages SSRN Quick Links * SSRN Solutions * Research Paper Series * Conference Papers * Partners in Publishing * Jobs & Announcements * Special Topic Hubs SSRN Rankings * Top Papers * Top Authors * Top Organizations About SSRN * Network Directors * Announcements * Contact us * FAQs * * * Copyright Terms and Conditions Privacy Policy All content on this site: Copyright (c) 2023 Elsevier Inc., its licensors, and contributors. All rights are reserved, including those for text and data mining, AI training, and similar technologies. For all open access content, the Creative Commons licensing terms apply. We use cookies to help provide and enhance our service and tailor content. To learn more, visit Cookie Settings. This page was processed by aws-apollo-l100 in 0.080 seconds