A hybrid intelligent system of ANFIS and CAPM for stock portfolio optimization

Article type: Research Article

Authors: Gunasekaran, M. | Ramaswami, K.S.

Affiliations: Department of Computer Applications, Park College of Engineering and Technology, Coimbatore, India | Department of Mathematics, Coimbatore Institute of Technology, Coimbatore, India

Note: [] Corresponding author. M. Gunasekaran, Department of Computer Applications, Park College of Engineering and Technology, Coimbatore, India. Tel.: +91 944 308 3837; E-mail: guna43@yahoo.com

Abstract: This paper addresses about an approach that suggests for stock portfolio optimization using the combination of Adaptive Neuro-Fuzzy Inference System (ANFIS) and Capital Asset Pricing Model (CAPM). Stock portfolio optimization aims to determine which of the stocks to be added to a portfolio based on the investor's needs, changing economic and market conditions. In order to construct an efficient prediction model, ANFIS is used to take decisions for forecasting the stock price using historical data of BSE SENSEX and well-known technical indicators. CAPM have been incorporated for portfolio optimization that can find the combination of stocks to offer an investor trade-off between expected return and risk of a portfolio. ANFIS-CAPM plays a decisive role in discovering portfolio strategies for investors and creates the optimal portfolio from a combination of stocks. Experimental results show that the proposed hybrid intelligent system ANFIS-CAPM yields better performance than existing portfolio models.

Keywords: Stock market forecasting, fuzzy logic, artificial neural network, portfolio optimization, Capital Asset Pricing Model (CAPM)

DOI: 10.3233/IFS-120736

Journal: Journal of Intelligent & Fuzzy Systems, vol. 26, no. 1, pp. 277-286, 2014