Can AI Replace Stock Analysts? Evidence from Deep Learning Financial Statements

43 Pages Posted: 2 May 2024 Last revised: 3 May 2024

See all articles by G. Nathan Dong

G. Nathan Dong

Boston College - Department of Finance

Date Written: March 31, 2024

Abstract

Equity research analysts have long been regarded as experts in predicting the performance of stocks. With the rapid advancements in artificial intelligence (AI), the question arises as to whether neural-network based deep-learning technology can surpass human analysts in this task. In this research, we apply a model-free deep-learning technique to equity research by training a simple neural-network (without pre-specified financial models or pre-defined accounting ratios) to predict 12-month-ahead stock price. Our AI model that runs on an inexpensive computer equipment is capable of processing vast amounts of financial statement raw data over a 14-year period in a fraction of the time and cost it would take a human analyst ($1,450 in equipment, 15 hours in time, and $2.5 in electricity, to be exact). It outperforms human analysts in 12-month-ahead target price forecasts by a large margin. Analysts and AI models are more likely to make similar predictions of the target price for firms that show signs of potential investment and future uncertainty, such as higher levels of cash, capital expenditures, and return volatility on the day of forecast. Overall, the results of this research support the notion that AI has the potential to replace human analysts in certain aspects of predicting financial performance.

Keywords: Analyst forecast, Target price, Artificial intelligence, Deep learning, Fintech

JEL Classification: C10, C45, G30, G23

Suggested Citation

Dong, Gang Nathan, Can AI Replace Stock Analysts? Evidence from Deep Learning Financial Statements (March 31, 2024). Available at SSRN: https://ssrn.com/abstract=4813310 or http://dx.doi.org/10.2139/ssrn.4813310

Gang Nathan Dong (Contact Author)

Boston College - Department of Finance ( email )

Carroll School of Management
140 Commonwealth Avenue
Chestnut Hill, MA 02467-3808
United States

HOME PAGE: http://sites.google.com/view/gang-nathan-dong

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

Paper statistics

Downloads
1,124
Abstract Views
3,481
Rank
37,088
PlumX Metrics