Title

Machine Learning and Short Positions in Stock Trading Strategies

Document Type

Book Chapter

Faculty

Faculty of Business and Law

School

School of Accounting, Finance and Economics

RAS ID

12921

Comments

This chapter was originally published as: Allen, D. E., Singh, A. , & Powell, R. (2011). Machine Learning and Short Positions in Stock Trading Strategies. In G.N. Gregoriou (Eds.). Handbook of Short Selling (pp. 467-478). Location: Elsevier.

Abstract

Investors may profit from either upward or downward movements in asset prices depending on whether they are long or short.To achieve immediate gains on their position they need to be able to predict the direction of short-term future price movements.The prediction of the direction of a price change is a classification problem. Customary statistical methods, such as linear logistic regression and discriminant analysis, are applied frequently to thisproblem. The development of more flexible methods, such as support vecto rmachine classification, offers practitioners potentially better and more powerful solutions. This chapter applies support vector machines (SVM )to predict the direction of price changes for a small set of DowJones Industrial Average stocks and tests them against the predictions obtained

This document is currently not available here.

 
COinS