A Hybrid Approach of Bayesian Structural Time Series With LSTM to Identify the Influence of News Sentiment on Short-Term Forecasting of Stock Price

In the financial sector, the stock market and its trends are highly volatile in nature. Recent studies have shown that news articles and social media analysis can have an immense impact on investors' opinion toward financial markets. Thus, the purpose of this study is to explore the relationship between news sentiment and stock market movement using information from different news agencies, business magazines, and financial portals. This study offers an application of the Bayesian structural time (BST) series model that is more transparent and facilitates better handling of uncertainty than the autoregressive integrated moving average (ARIMA) model and the vector autoregression (VAR) method by using prior information about the structure of the model. One of the main pitfalls of this model is the presumption of linearity. The long short-term memory (LSTM) model is a nonlinear model that can capture various nonlinear structures present in the data set. We propose a hybrid model, which combines the LSTM model with the BST model along with the regression component that captures information from different news sources to identify market predictors. The proposed model detects unusual behavior or anomalous pattern of the stock price movement, which makes our model superior compared to the traditional methods. Our new hybrid model accumulates error with lower rates (3.5%) and shows a remarkable performance over some of the other existing hybrid models, such as AR-MLP, ARIMA-LSTM, and VAR-LSTM model.