Using Machine Learning Algorithms to Find Patterns in Stock Prices

FEDEA Working Paper No. 2006-12

20 Pages Posted: 27 Mar 2006  

Pedro N. Rodriguez

Complutense University of Madrid - Facultad de Ciencias Económicas y Empresariales - Departamento de Estadística e Investigación Operativa II

Simon Sosvilla-Rivero

Complutense Institute for International Studies

Date Written: October 25, 2006

Abstract

We use a machine learning algorithm called Adaboost to find direction-of-change patterns for the S&P 500 index using daily prices from 1962 to 2004. The patterns are able to identify periods to take long and short positions in the index. This result, however, can largely be explained by first-order serial correlation in stock index returns.

Keywords: Direction-of-change predictability, Machine learning algorithms, Adaboost

JEL Classification: C45, G11, G14

Suggested Citation

Rodriguez, Pedro N. and Sosvilla-Rivero, Simon, Using Machine Learning Algorithms to Find Patterns in Stock Prices (October 25, 2006). FEDEA Working Paper No. 2006-12. Available at SSRN: https://ssrn.com/abstract=893141 or http://dx.doi.org/10.2139/ssrn.893141

Pedro N. Rodriguez

Complutense University of Madrid - Facultad de Ciencias Económicas y Empresariales - Departamento de Estadística e Investigación Operativa II ( email )

Carretera de Humera s/n
Madrid 28223, Madrid 28223
Spain

HOME PAGE: http://www.pnrodriguez.com

Simon Sosvilla-Rivero (Contact Author)

Complutense Institute for International Studies ( email )

Carretera de Humera s/n
Madrid, Madrid 28223
Spain
+34913932626 (Phone)

HOME PAGE: http://www.ucm.es/info/ecocuan/ssr/

Register to save articles to
your library

Register

Paper statistics

Downloads
922
rank
21,700
Abstract Views
3,499
PlumX