Applications Using Hybrid Intelligent Decision Support Systems for Selection of Alternatives under Uncertainty and Risk

Alternative selection of a portfolio has been a challenging research area in finance and investment decision making. Recent advances in single Decision Support Systems (DSS), soft computing and machine learning models are to solve the problems in selection of alternatives under uncertain market and risk environments. These models have not considered concurrently uncertain values including quantitative and qualitative stock-market factors, together with experts’ feelings and preferences about market dynamics. This affects the capability of an investment system to deal with various market conditions. The study is to solve the existing problems in the selection of the most appropriate alternatives (companies, company groups and stocks) at the right time for stock trading. In this paper, we propose Hybrid Intelligent DSS models using Kansei Evaluation integrated with other single DSS techniques, aiming to aggregate experts’ preferences with the selection of the most suitable stocks to achieve investment returns and risk reduction by dealing with complex situations in market dynamics. The proposed models have been tested and performed well in both simulated trading results and real-world stock trading on the HOSE, HNX (Vietnam), NYSE and NASDAQ (US) stock markets to validate the integrated DSS methods in various stock markets. In order to evaluate the effectiveness of this approach, experimental results show that the proposed approach performs better than other current DSS methods and hybrid models to select the right alternatives at the right trading time under uncertainty and risk.