Portfolio selection with fuzzy synthetic evaluation and genetic algorithm

Abstract

Purpose

The purpose of this paper is to present a new technique to portfolio selection using a genetic algorithm (GA) and fuzzy synthetic evaluation (FSE). Portfolio selection is a multi-objective/criteria decision-making problem in financial management.

Design/methodology/approach

The proposed approach solves the problem in two stages. In the first stage, by using a GA and FSE, the weight of criteria will be calculated. Euclidean distance between the computed overall performance evaluation and the surveyed overall performance evaluation is used to determine the weight of criteria. In the second stage, by using a GA and FSE, portfolios will be prioritized. A multi-objective GA is used to determine return and risk in the efficient frontier. A decision making approach is based on FSE to select the best portfolio from among the solutions obtained by a multi objective GA.

Findings

The main advantage of the proposed approach is to help an investor to find a portfolio which has best performance, and portfolio selection does not rely on expert knowledge.

Originality/value

The value of the paper is in it using a new approach to determine the weight of criteria and portfolio selection. It surveys firms’ performance in the stock market, based on which the weight of criteria will be determined and portfolios will be prioritized.

Citation

Nayebpur, H. and Nazem Bokaei, M. (2017), "Portfolio selection with fuzzy synthetic evaluation and genetic algorithm", Engineering Computations, Vol. 34 No. 7, pp. 2422-2434. https://doi.org/10.1108/EC-03-2017-0084