Stock Portfolio Selection using Data Mining Approach

Abstract

Once it is decided that investment is to be made in the stock, the obvious question which arises is: which all stocks should be purchased? Past performance will not guarantee the future, but it is still worthwhile to evaluate the investments based on their ability to deliver consistent returns with minimal risk. Therefore, the ability to generate most profitable return from short term stock trading is a crucial factor for traders and investors. The paper focuses on a comparative study between two data mining techniques, Logistic Regression and Neural Network for stock portfolio selection using a set of fundamental and technical parameters.