search for




 

A study on asset allocation strategy using Google trends
Journal of the Korean Data & Information Science Society 2020;31:173-86
Published online January 31, 2020;  https://doi.org/10.7465/jkdi.2020.31.1.173
© 2020 Korean Data and Information Science Society.

Eun Chong Kim1 · Dong Won Lee2

1Qraft Technologies
2Department of Industrial Engineering, Yonsei University
Correspondence to: Graduate student, Department of Industrial Engineering, Yonsei University, Seoul 03722, Korea. E-mail: jungleofsj@naver.com
Received November 10, 2019; Revised December 30, 2019; Accepted January 4, 2020.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
The purpose of this study is to apply Google Trends to asset allocation strategies. This takes advantage of the fact that market participants are followed by information retrieval for investment decisions during times of market downturn. First, we select a word index with precedence of stocks and bonds. After that, we construct an investment strategy using Google Trends in each word. Finally, the investment ratio is optimized by rebalancing each investment strategy. This confirms that strategies using Google Trends can generate stable returns over the performance of the traditional 60/40 portfolio. In addition, it was confirmed that optimizing the strategy using each word using Genetic Algorithm improved the performance compared to the strategy of investing the same weight with each strategy using each word.
Keywords : Asset allocation, genetic algorithm, Google trends index, portfolio investment strategy, 60/40 portfolio.