Building long/short portfolios using rule induction

Abstract
We approach stock selection for long/short portfoliosfrom the perspective of knowledge discovery indatabases and rule induction: given a database ofhistorical information on some universe of stocks,discover rules from the data that will allow one topredict which stocks are likely to have exceptionallyhigh or low returns in the future. Long/short portfoliosallow a fund manager to independently addressvalue-added stock selection and factor exposure, andare a popular tool in financial...

This publication has 10 references indexed in Scilit: