A Spatial-Temporal Attention Based BiLSTM For Stock Index Prediction

In the environment of increasing volatility in financial markets and international capital flows,the accuracy and robustness of predictions are key factors in financial decision-making.Predicting stock price indices has been an active area of research.Among them,many studies use data mining techniques,including artificial neural networks.However,most studies have shown that artificial neural networks have certain limitations in terms of learning data patterns,because stock market data has huge noise and complex dimensions,correlation problems between its external properties,and external influences in long-term predictions can lead to increased stock price volatility.Artificial neural networks have excellent learning capabilities,but they are often faced with inconsistent and unpredictable noisy data.In addition,sometimes the amount of data is too large,and the learning of patterns may not work well.In addition,in long-term forecasting,the redundancy of features and the complexity of the model cause the predictions model to be unable to extract the price and time change relationship accurately.The presence of continuous data and large amounts of data poses serious problems for extracting valid information from raw data.Reduction and transformation of uncorrelated or redundant features can reduce uptime and produce universal results.In order to solve the above problems,this paper uses the attention mechanism-based bidirectional long short-term memory neural network(Bi LSTM)to test the effectiveness of the closing price of Hong Kong Hang Seng Index.Among them,spatial attention mechanism is used to capture the correlation between input indicators and give them distinctive weights.Temporal attention mechanism is used to describe the time correlation of data to solve the time dependence problem in long-term prediction and give distinctive weights to time steps.Besides,Bi LSTM neural network is used to fit the data and construct prediction model.This paper also hopes to judge the effectiveness of the proposed model by comparing the performance of other recent artificial neural network model in predicting market value,including four neural network methods based on attention mechanism and six baseline methods.Experimental results show that the spatial attention mechanism proposed in this paper can achieve a higher accuracy than the traditional principal component analysis dimensionality reduction method,indicating that the spatial attention mechanism can capture the correlation between feature vectors,simplify the model effectively,and improve the generalization performance of the model.In addition,the temporal attention mechanism proposed in this paper can capture the relationship between stock price and time change in long-term prediction,so it always performs better in medium-and long-term prediction than models that do not add temporal attention mechanism under the same conditions.Bi LSTM based on the dual-dimensional attention mechanism can achieve more accurate prediction of the closing price of HSI stock indexes in short-,medium-and long-term compared with the current popular stock index prediction methods.Based on these two attention mechanisms,Bi LSTM is not only able to select the most relevant input features adaptively,but also to capture the long-term temporal correlation of time series appropriately.The conclusion of this paper provides investors with a more effective investment strategy,and provides practical insights and potentially useful directions for further research on how deep learning network can be effectively used in stock market analysis and prediction.