A novel approach on hybrid Support Vector Machines into optimal portfolio selection

Abstract

The efficient representation of the accurate corporate value on the stock price is vital to investors and fund managers that desire to optimize the net worth of the overall stock portfolio. Although Efficient Market Hypothesis sets limits, the practice of markets is an ideal place of manipulation, and corruption on prices. The accounting statements, evaluated by Support Vector Machines and the SVM Hybrids under Genetic Algorithms provide excellence in portfolio selection. A specific Neuro-genetic Hybrid SVM outperformed all examined SVM models being a powerful tool in financial analysis.