search for


Scoring model to determine trade timing based on genetic algorithm
Journal of the Korean Data & Information Science Society 2018;29:735-45
Published online May 31, 2018
© 2018 Korean Data and Information Science Society.

Ki Hwan Jo1 · Seung Hwan Jeong2 · Kyung Sup Kim3 · Kyong Joo Oh4

1Division of Investment Information Engineering, Yonsei University
234Department of Industrial Engineering, Yonsei University
Correspondence to: Professor, Department of Industrial Engineering, Yonsei University, Seoul 03722, Korea. E-mail:
Received March 5, 2018; Revised March 21, 2018; Accepted April 1, 2018.
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.
In order to respond to the complicated financial market, it became very important to grasp the point of sale precisely. The existing studies that use the technical indicators to find the trading point have a disadvantage that they are limited to specific situations. This study suggests a scoring model that overcomes the disadvantages of these previous studies. The scoring model presented in this study can be applied to various financial situations because it uses 21 variables related to stock price and moving average as input variables and has been optimized through genetic algorithm technique. For the empirical analysis of the proposed model, KOSPI data for the past 12 years (2005 ∼ 2016) were used and the sliding window technique was applied to analyze. In this model, if the market is a liege length, it will take a holding strategy, and if it is a trend, it will be able to cope with an excessive decline in the market by buying or selling at a rising price, resulting in better performance than the method using existing technical indicators.
Keywords : Genetic algorithm, scoring model, sliding window, trading time.