Portfolio selection using Maximum-entropy gain loss spread model: A GA based approach

This paper presents a multi-objective portfolio selection model solved using genetic algorithms. In this approach an entropy measure has been added so that a well-diversified portfolio is generated. Based on literature survey, it was observed that there is a need of new portfolio selection model which is free from the limitations as observed in existing models. Hence emphasis has been put on proposing a new portfolio selection model with the aim of achieving high returns and efficient diversification. We propose a new portfolio selection model and name it as Maximum-entropy Gain Loss Spread model (ME-GLS). The proposed model overcomes the limitations identified in the existing models available in literature. We have given a comparative analysis of our proposed method with relevant methods available in literature. Since the proposed model achieves higher returns and at the same time achieves higher degree of diversification which implies risk is also minimized at the same time.