A Mutual Fund Investment Method Using Fruit Fly Optimization Algorithm and Neural Network

Abstract:

This paper presents a method to construct a profitable portfolio of mutual funds for investors. This method comprises two stages. In the first stage, the DEA, Sharpe and Treynor indices of mutual funds and the monthly rates of return (ROR) of mutual funds are used to select a mutual fund portfolio. In the second stage, the linear regression model, the Fruit Fly Optimization Algorithm (FOA) and the General Regression Neural Network (GRNN) are used to construct a prediction model for the net asset values of each of the constituent mutual funds of the portfolio. The trade decision of a selected mutual fund is then made based on the rise or fall of its net asset value. The empirical results showed that, compared to other combinations, the combination of using Sharpe index for portfolio selection and the GRNN optimized with FOA for net asset value prediction offered the best accumulated return rate for the mutual fund portfolio investment.

• Periodical: Applied Mechanics and Materials (Volumes 571-572)
• Pages: 318-325
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.571-572.318
• Online since: June 2014
• Authors: Tsu Hua Huang*, Yung Ho Leu
• Keywords: Data Envelopment Analysis, Fruit Fly Optimization Algorithm, General Regression Neural Network, Mutual Fund, Neural Network and Linear Regression

References

[1] A. Charnes, W. W. Cooper and E. Rhodes: Measurement the Efficiency of Decision Making Units. European Journal of Operational Research Vol. 2, Issue 6 (1978), pp.429-444.

DOI: 10.1016/0377-2217(78)90138-8

[2] B.P.S. Murthi, Yoon k. Choi and Preyas Desai: Efficiency of Mutual Funds and Portfolio Performance Measurement: A Non-Parametric Approach. European Journal of Operational Research, Vol. 98, Issue 2 (1997), pp.408-418.

DOI: 10.1016/s0377-2217(96)00356-6

[3] Chien-Jen Huang, P-W Chen and W-T Pan: Multi-stage Data Mining Technique to Build the Forecast Model for Taiwan Stocks. Neural Comput. & Applic., Online First TM (2011).

DOI: 10.1007/s00521-011-0628-0

[4] D.F. Specht A General Regression Neural Network, IEEE Trans. Neural Networks, Vol. 2, No. 6 (1991), pp.568-576.

DOI: 10.1109/72.97934

[5] J.H. Friedman: Multivariate adaptive regression splines. Annals of Statistics, Vol. 19, No. 1 (1991) pp.1-141.

[6] Jiah-Shing Chen, Jia-Li Hou, Shih-Min Wu and Ya-Wen Chang-Chien: Constructing investment strategy portfolios by combination genetic algorithms. Expert Systems with Applications, Vol. 36, Part 2 (2009), p.3824–3828.

DOI: 10.1016/j.eswa.2008.02.019

[7] J.J. Hopfield: Neural Networks and Physical Systems with Emergent Collective Computational Abilities. Proc. Natl. Acad. Sci. Vol. 79, No. 8 (1982), pp.2554-2558.

DOI: 10.1073/pnas.79.8.2554

[8] Jui-Fang Chang: Using investment satisfaction capability index based particle swarm optimization to construct a stock portfolio. Information Sciences, Vol. 181, No. 14 (2011), p.2989–2999.

DOI: 10.1016/j.ins.2010.05.008

[9] J. L. Treynor: How to Rate Management Investment Funds. Harvard 84 Business Review, Vol. 43 (1965), pp.63-75.

[10] Leorey Marquez and Tim Hill: Function Approximation Using Backpropagation and General Regression Neural Networks. In Proceeding of the Twenty-Sixth Hawaii International Conference on System Science, Vol. 4 (1993), pp.607-615.

DOI: 10.1109/hicss.1993.284240

[11] McMullen, Patrick R. and Robert A. Strong: Selection of Mutual Funds Using Data Envelopment Analysis. Journal of Business and Economic Studies, Vol. 4, Issue 1 (1998), pp.1-12.

[12] Meryem Duygun Fethi and Fotios Pasiouras: Assessing bank efficiency and performance with operational research and artificial intelligence techniques: A survey. European Journal of Operational Research, Vol. 204, issue 2 (2010), p.189–198.

DOI: 10.1016/j.ejor.2009.08.003

[13] M. J. Ferrell: The Measurement of Productive Efficiency. Journal of theRoyal Statistical Society, Vol. 120, Part 3 (1957), pp.253-281.

[14] Peng-Wen Chen, Wei-Yuan Lin, Tsui-Hua Huang and Wen-Tsao Pan: Using Fruit Fly Optimization Algorithm Optimized Grey Model Neural Network to Perform Satisfaction Analysis for E-Business Service. Applied Mathematics & Information Sciences, Vol. 7, No. 2L (2013).

DOI: 10.12785/amis/072l12

[15] Razieh Bahrani and Nader Khedri: Evaluation of Relative Efficiency and Performance of Companies Using Data Envelopment Analysis (DEA) Approach. Elixir International Journal, Elixir Fin. Mgmt. 56 (2013) , pp.13299-13304.

[16] Ruay-Shiung Chang, Jih-Sheng Chang and Po-Sheng Lin: An ant algorithm for balanced job scheduling in grids. Future Generation Computer Systems, Vol. 25, Issue 1 (2009), p.20–27.

DOI: 10.1016/j.future.2008.06.004

[17] Wen-Tsao Pan: A New Fruit Fly Optimization Algorithm: Taking the Financial Distress Model as An Example. Knowledge-Based Systems, Vol. 26 (2012), pp.69-74.

DOI: 10.1016/j.knosys.2011.07.001

[18] Wen-Tsao Pan: Performing stock price prediction use of hybrid model. Chinese management studies : CMS. -Bingley : Emerald, Vol. 4, Issue 1 (2010), pp.77-86.

DOI: 10.1108/17506141011033016

[19] W. F. Sharpe: Mutual Fund Performance. Journal of Business, vol. 39, No. 1, Part 2 (1966), pp.119-138.