Stock market prediction based on interrelated time series data

In this paper, we propose a stock market prediction method based on interrelated time series data. Though there are a lot of stock market prediction models, there are few models which predict a stock by considering other time series data. Moreover it is difficult to discover which data is interrelated with a predicted stock. Therefore we focus on extracting interrelationships between the predicted stock and various time series data, such as other stocks, world stock market indices, foreign exchanges and oil prices. We test our method for predicting the daily up and down changes in the closing value by using discovered interrelationships, and experimental results show that our methods can predict stock directions well, especially in the manufacturing industry.