Time Series Analysis of Global Automakers Stock Price Clustering

In the paper, we describe the stock price data analysis using the machine learning based hierarchical clustering method. The data we used are the top 100 global automakers' stock prices from 2018 to 2019. The companies' countries are Japan, US and Germany. We analyzed sequentially a bi-month data for the two years. Then we found that when the stock price significantly decreased, there could clearly appear a cluster by a country. In the global turmoil period by the US-China trade friction in 2018, we could identify the Japan cluster and the US cluster with clear boundaries. To verify the hypothesis, we traced the time series changes of the clusters through the two years. As a result, we proved the hypothesis was correct, as far as the period was what we used.