CLUSTERING STOCK DATA FOR MULTI-OBJECTIVE PORTFOLIO OPTIMIZATION

Abstract

Portfolio selection is a vital research field in modern finance. Multi-objective portfolio optimization problem is the portfolio selection process that results in the highest expected return rate and the lowest identified risk among the various financial assets. This paper proposes a model that can efficiently suggest a portfolio that is worth investing. First, a cluster analysis model is introduced in order to categorize a huge amount of stock data into several groups based on their associated return rate and the risk. Several validity indexes are used to select the optimal number of clusters/stocks to be included in the portfolio. Finally, the multi-objective genetic algorithm is used to build portfolio optimization with highest return rate and lowest risk. The proposed model is tested on the data obtained from the Stock Exchange of Thailand.