Improving Earnings Predictions and Abnormal Returns with Machine Learning

SYNOPSIS Using stepwise logit regression, Ou and Penman (1989) predicts the sign of future earnings changes and uses these predictions to form a profitable hedge portfolio. Increases in computing power and advances in machine learning allow us to extend Ou and Penman (1989) using more data, computer...

Full description

Saved in:
Bibliographic Details
Published in:Accounting horizons 2022-03, Vol.36 (1), p.131-149
Main Authors: Hunt, Joshua O. S., Myers, James N., Myers, Linda A.
Format: Article
Language:English
Subjects:
Artificial intelligence
Earnings
Earnings forecasting
Financial statement analysis
Machine learning
Prediction models
Predictive analytics
Trading
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:SYNOPSIS Using stepwise logit regression, Ou and Penman (1989) predicts the sign of future earnings changes and uses these predictions to form a profitable hedge portfolio. Increases in computing power and advances in machine learning allow us to extend Ou and Penman (1989) using more data, computer intensive forecasting algorithms, and modern prediction models. Stepwise logit still provides good predictions and can be used to form a trading strategy that generates small abnormal returns, but random forest significantly improves forecast accuracy and returns. The models identify different variables as being important for prediction in high tech and manufacturing, but this does not lead to better predictions or higher returns. Results confirm Ou and Penman's (1989) finding that financial statement information is useful for investment decisions, and suggest that machine learning techniques can be useful in a variety of accounting contexts.
ISSN:0888-7993
1558-7975
DOI:10.2308/HORIZONS-19-125