Clustering of ETF Data for Portfolio Selection during Early Period of Corona Virus Outbreak

Market prediction is important for well-organized portfolio management with wise selection of investments. As share market prices change dynamically depending on various factors, manual tracking is difficult. Machine learning tools are now becoming popular for automatic prediction and recommendation for stock trading. In this work, the objective is to apply popular machine learning techniques for time series clustering on real ETF (Exchange Traded Funds) data and conduct a performance comparison of the results. Here four clustering methods are used which are: 1) Hierarchical clustering with Euclidean distance, 2) k-means clustering with a) Euclid distance (ED) and b) Dynamic Time Warping (DTW) as the distance measures, 3) k-means with shape based distance measure (k-Shape) and 4) k-means with a newly developed shape based transformation along with DTW as a similarity measure LTAA (Log Time Axis Area). The clustering results on 20 ETF data from Tokyo Stock Exchange have been analyzed. It is found that the trends of the stock market of different funds during the early period after the outbreak of coronavirus can be categorized into roughly three clusters. The big cluster is representing ETFs suffering loss and two smaller clusters, one of them showing no damage and the other comprised of ETFs suffering loss but showing varying degrees of recovery with time.