A Fuzzy Rule-Based System for Portfolio Selection Using Technical Analysis

In this article, we propose an automatic trading system for portfolio selection that incorporates an investor's trading strategy (aggressive, conservative, or neutral). The system employs technical indicators to forecast assets' future price behavior. In particular, it clusters assets into three groups: 1) the promising assets are clustered in the “Buy” group, 2) the assets in danger of imminent losses are clustered in the “Sell” group, and 3) the remaining assets are clustered in the “Hold” group. We develop a gradient-based fuzzy rule system that can identify the three groups based on the technical indicator values of the cluster centers. We also develop a labeling algorithm as a corrective measure in case the fuzzy rule-based system identifies more than one group as buy, sell, or hold. Subsequently, we input the clusters to a credibilistic portfolio optimization model that models asset returns using coherent fuzzy numbers. We employ a genetic algorithm to solve the optimization model that exploits the problem's special structure. The proposed methodology is illustrated with a case study of the components of the NASDAQ-100 index.