search for


Asset allocation strategy using hidden Markov model and genetic algorithm
Journal of the Korean Data & Information Science Society 2019;30:33-44
Published online January 31, 2019;
© 2019 Korean Data and Information Science Society.

Eun Chong Kim1 · Kyong Joo Oh2

12Department of Industrial Engineering, Yonsei University
Correspondence to: Professor, Department of Industrial Engineering, Yonsei University, Seoul 03722, Korea. E-mail:
Received December 30, 2018; Revised January 11, 2019; Accepted January 11, 2019.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License ( which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
The study uses the hidden Markov model to identify the aspects of individual events and use them to propose an investment strategy that effectively utilizes price trends. An empirical analysis was conducted on the KOSPI200 stocks from January 2001 to September 2018. The proposed model showed better investment performance than strategies using conventional pricing momentum strategies. Analysis of the results showed that the exposure of the UMD (up-minus-down, momentum) factor was greatly improved. The results of this study are as follows. We analyze the effect of selection of stocks using hidden Markov model and the optimal investment ratio of stocks using genetic algorithm. These results show that it can be useful for future asset allocation strategies.
Keywords : Genetic algorithm, hidden markov model, portfolio investment strategy, price momentum.