A portfolio selection by SOM and an asset allocation of risk/nonrisk assets by fuzzy reasoning using the selected brands

A portfolio is an useful method to calculate the rate of expected earnings and risks based on changes in stock prices. However, past methods such as the fundamental analysis, the technical analysis and etc. are not proposed as a decision support system available for real investments. On the other hand, speaking about the asset allocation, those methods determine asset allocation ratio using general indices such as TOPIX independently of the portfolio selections. This paper describes a novel decision support system for assisting in actual investment decisions. First, the system makes a stock investment brand selection using SOM (self-organizing maps). Secondly, the system calculates asset allocation ratio of risk/nonrisk assets using both fuzzy reasoning and the management indices of the brands selected by SOM. We apply this method to actual stock price data and show better results than those by TOPIX. Finally, we discuss an effectiveness of the proposed support system against a steep fall in stock prices, such as IT Bubble collapse that began in 2000.

1 Introduction

The portfolio selection was proposed by H. M. Markowitz to calculate an investment efficiency [1], [2]. The technical analysis, the fundamental analysis, the random walk analysis are famous techniques for the portfolio. Also, there are techniques using soft computing technology such as the fuzzy theory, the neural networks, and the genetic algorithm. However, decision support systems available for real investments are not proposed yet. In real investments, we have to consider a risk of big loss due to the selection of brands in the similar status in changes of business trend like the collapse of a bubble economy. A solution of the risk aversion is the selection of good business status brands and the rejection of similar business status brands to them.