Stock price forecasting based on the relationship among Asian stock markets using deep learning

The stock price fluctuation of one country can be influenced by the movement of the stock price of other countries implying that there exists some relationship among various stock markets. This study examines the interrelationship among Asian stock markets and forecasts the stock market on the basis of the relationship that exists among Asian stock markets. The interrelationship is tested by using the Granger causality (GC) test and Pearson's correlation (PC) matrix. Further, a deep learning model namely a long short term memory (LSTM) neural network is utilized to forecast the stock price of one country by using the price of other countries that have a correlation and causal relationship with the target stock market. PC matrix shows that there exists a strong correlation among Asian stock markets. Results from the GC show that there exists a unidirectional relationship between Sensex and NIKKEI 225 to SSE composite index, Sensex to NIKKEI 225, and Sensex and TSEC weighted index to KOSPI composite index and a bi-directional relationship among Sensex, TSEC weighted index and Hang Seng index. Experimental results show that GC and LSTM-based model namely GC-LSTM shows better forecasting performance in comparison to PC and LSTM-based model termed as PC-LSTM.

Automated summary

The stock price fluctuations of different countries are interrelated, and this study examines the interrelationship among Asian stock markets and forecast the stock market based on this relationship. The Granger causality (GC) test and Pearson's correlation (PC) matrix are used to test the interrelationship. The results show a strong correlation among Asian stock markets, and the GC-LSTM model outperforms the PC-LSTM model in forecasting performance.