Stock Price Forecasting with Deep Learning: A Comparative Study

Mathematics

Arjun Neupane¹  TejBahadur Shahi¹  William Guo¹  Ashish Shrestha² 

[1] Central Queensland University, North Rockhampton, Rockhampton QLD 4702, Australia;Department of Electrical and Electronics Engineering, Kathmandu University, Kathmandu 44613, Nepal;

关键词: deep learning;    long short-term memory (LSTM);    gated recurrent unit (GRU);    financial news sentiments;    stock market forecasting;   

DOI  :  10.3390/math8091441

来源: DOAJ

【 摘 要 】

The long short-term memory (LSTM) and gated recurrent unit (GRU) models are popular deep-learning architectures for stock market forecasting. Various studies have speculated that incorporating financial news sentiment in forecasting could produce a better performance than using stock features alone. This study carried a normalized comparison on the performances of LSTM and GRU for stock market forecasting under the same conditions and objectively assessed the significance of incorporating the financial news sentiments in stock market forecasting. This comparative study is conducted on the cooperative deep-learning architecture proposed by us. Our experiments show that: (1) both LSTM and GRU are circumstantial in stock forecasting if only the stock market features are used; (2) the performance of LSTM and GRU for stock price forecasting can be significantly improved by incorporating the financial news sentiments with the stock features as the input; (3) both the LSTM-News and GRU-News models are able to produce better forecasting in stock price equally; (4) the cooperative deep-learning architecture proposed in this study could be modified as an expert system incorporating both the LSTM-News and GRU-News models to recommend the best possible forecasting whichever model can produce dynamically.

【 授权许可】

Unknown