An Exploratory Comparison of LSTM and BiLSTM in Stock Price Prediction
Published in Inventive Communication and Computational Technologies, 2023
Recommended citation: Viet, N.Q., Quang, N.N., King, N., Huu, D.T., Toan, N.D., Thanh, D.N.H. (2023). "An Exploratory Comparison of LSTM and BiLSTM in Stock Price Prediction." Inventive Communication and Computational Technologies. ICICCT 2023. Lecture Notes in Networks and Systems, vol 757. Springer, Singapore.
Forecasting stock prices is a challenging topic that has been the subject of many studies in the field of finance. Using machine learning techniques, such as deep learning, to model and predict future stock prices is a potential approach. Long short-term memory (LSTM) and bidirectional long short-term memory (BiLSTM) are two common deep learning models. The finding of this work is to discover which activation function and which optimization method will influence the performance of the models the most. Also, the comparison of closely related models: vanilla RNN, LSTM, and BiLSTM to discover the best model for stock price prediction is implemented. Experimental results indicated that BiLSTM with ReLU and Adam method achieved the best performance in the prediction of stock price.