結合技術指標改善投資組合效益之研究

Combining technical indexes to improve portfolio performance

吳健豪(Chien-Hao Wu)

指導教授 ： 林志麟

元智大學/資訊學院/資訊管理學系/碩士(2013年)

https://doi.org/10.6838/YZU.2013.00113

摘要

由Markowitz所提出的MV模型(Mean-Variance Model)常應用於投資組合最佳化問題，其效率前緣包含了所有的最佳投資組合的集合。在投資期間，買賣時機為投資人進行投資時考量的重要因素之一，而技術指標被廣泛使用於擇時的參考依據。故本研究首先結合MV模型與隨機指標建構了三種方法，試圖各取其MV模型與隨機指標的優點，建立適合不同風險喜好的投資組合策略。然而為了在同樣的技術指標下尋找可適解，文中也利用了基因演算法求解。並於文末探討本研究所提出之四種方法和傳統方法之間的績效差異

關鍵字

投資組合最佳化 ； MV模型 ； 技術指標

並列摘要

The mean-variance model proposed by Harry Markowitz is widely used for portfolio optimization. It helps the investors to allocate their capital to a number of assets, however, it does not guide the investors when to buy these assets. In contrast, technical indexes are widely used to help the investors to decide when to buy/sell the assets. In this thesis, we integrate the mean-variance model and technical indexes to propose three investment strategies. Performance study is conducted to compare the performance of these methods against the traditional approaches.

並列關鍵字

portfolio optimization ； mean-variance model ； technical indexes

參考文獻

[1]Skolpadungket, P., B. Univ. of Bradford, and K.H. Dahal, N., Portfolio optimization using multi-objective genetic algorithms. Evolutionary Computation, 2007: p. 516 - 523.

[2]Chopra, V.K., C.R. Hensel, and A.L. Turner, Massaging Mean-Variance Inputs: Returns from Alternative Global Investment Strategies in the 1980s. Management Science, 1993. 39(7): p. 845-855.

[3]Chopra, V.K. and W.T. Ziemba, The Effect of Errors in Means, Variances, and Covariances on Optimal Portfolio Choice. The Journal of Portfolio Management, 1993. 19(2): p. 6-11.

[4]Chen, J.-S., et al., Constructing investment strategy portfolios by combination genetic algorithms. Expert Systems with Applications, 2009. 36(2): p. 3824–3828.

[6]Berm#westeur059#dez, J.D., J.V. Segura, and E. Vercher, A multi-objective genetic algorithm for cardinality constrained fuzzy portfolio selection. Fuzzy Sets and Systems,2012. 188(4): p. 16-26.