近年來金融海嘯及通貨緊縮的衝擊,投資者若單憑市場動向來猜測投資標的,極容易在市場波動中造成龐大的損失。投資組合是同時需要考量預期收益及風險的多目標問題,當股票數愈多則其問題的複雜度也就愈高,若使用二次規劃法來求解,可能耗時很久而沒有效率,因此需運用更有效率的啟發式演算法來求得最佳解。相較於其他啟發式演算法而言,差分演算法具有參數設定少、快速收斂及容易實作等特性的優勢,因此本研究嘗試利用差分演算法來解決投資組合最佳化的問題。經實驗結果發現,差分演算法在解的品質及求解效率上有不錯的效益,也證明差分演算法應用在投資組合最佳化問題的可行性及有效性。
Because of the impact of the financial tsunami and economic recession, it is easy for the investors to get huge losses in the stock market. Portfolio optimization is a multi-objective problem in which we expect to get high expected returns and low risks. To solve the problem an efficient heuristic algorithm must be used to obtain optimal solution. The objective of this paper is to use differential evolution (DE) for portfolio optimization. Compared to other heuristic algorithms, differential evolution has three advantages: fewer parameters, fast convergence and easy implementation. The experimental results show that differential evolution has good performance in solution quality and computation time. We also show that differential evolution is an effective approach to solve portfolio optimization problems.