An Application of Multi-Objective Genetic Algorithms on Fundamental Selection Strategy

• Main Authors: Hui-Min Liu, 劉慧敏
• Other Authors: Jiah-Shing Chen
• Format: Others
• Language: zh-TW
• Published: 2002
• Online Access: http://ndltd.ncl.edu.tw/handle/53914353815403219320

碩士 === 國立中央大學 === 資訊管理研究所 === 90 === Real-world problems involve multiple objectives that need to be optimized simulta-neously. So does investment problem. In this paper, we propose a framework of stock portfo-lio selection strategies based on MOGA and using fundamental data of company’s financial statements. MOGA is well suited to solve these multi-objective optimization problems since a family of “acceptable” solutions — a Pareto set — can be identified by different individuals through the evaluation process. We implement the framework with VEGA, a kind of MOGA method. Our preliminary experiments show that the results of these MOGA-based strategies are promising.