Using Boosting for Financial Analysis and Performance Prediction: Application To S&P 500 Companies, Latin American ADRs and Banks
Germán G. Creamer
Stevens Institute of Technology - Wesley J. Howe School of Technology Management
University of California, San Diego
Computational Economics, Vol. 36, No. 2, pp. 133-151
This paper demonstrates how the boosting approach can support the financial analysis functions in two ways:
1. As a predictive tool to forecast corporate performance, and rank accounting and corporate variables according to their impact on performance, and
2. As an interpretative tool to generate alternating decision trees that capture the non-linear relationship among accounting and corporate governance variables that determine performance.
We compare our results using Adaboost with logistic regression, bagging, and random forests. We conduct 10-fold cross-validation experiments on one sample each of S&P 500 companies, American Depository Receipts (ADRs) of Latin American companies and Latin American banks.
Adaboost results indicate that large companies perform better than small companies, especially when these companies have a limited long-term assets to sales ratio. Performance improves for large LAADR companies when the country of residence is characterized by a weak rule of law. In the case of S&P 500 companies, performance increases when the compensation for top officers is mostly variable.
Number of Pages in PDF File: 10
Keywords: Financial analysis, machine learning, adaboost, data mining
JEL Classification: C49, C63, G24
Date posted: May 15, 2010 ; Last revised: February 20, 2013