SVM-PCA – An Emerging Way to Efficient Stock Selection from Nifty Basket : A Detailed Work on Support Vector Machine - Principal Component Analysis

Traditionally it has been observed that R², Sharpe Ratio and Treynor Ratio are used to find efficient stocks from a broad based market. The CNX Nifty is a well diversified 50 stock index accounting for 23 sectors of the economy. It is used for a variety of purposes such as benchmarking fund portfolios, index based derivatives and index funds. However it has been observed lately (specially from 2008 onwards), that alternate methods are getting used more often by both educationists and industry experts at the same time. They are using biological algorithms coupled with mechanical machine learning tools, following a complex financial logic, to derive both stock trend and efficient basket of stocks. This study presents the results of combined statistical algorithms used for efficient stock selection even within a supposedly efficient basket called CNX Nifty. Namely PCA (Principal Component Analysis) and SVM (Support Vector Machines) have been combined to carry out a rigorous test on CNX Nifty basket. These algorithms when used in tandem could produce accurate results to identify efficient stocks (stocks which will follow Efficient Market theory by Harry Markowitz)