Stock Market Forecasting with LSTM and Sentiment Analysis

Abstract

Stock market is an industry where lots of data is generated daily and benefits are reaped on the basis of accurate prediction. Many people invest in stock market having some prediction and more luck. A decision in stock market plays an important role in the investor’s life. Also, stock market is a very complex system and non-linear in nature. So, then it is very difficult to analyse all the impacting factors before making a decision. Making decision with traditional techniques may be time consuming and may not ensure the reliability of the prediction. Data from stock market is a time series data and different variations of neural networks are widely being used for stock forecasting and prediction problems. Among various architectures of deep neural network, LSTM is one of the design that supports time steps of arbitrary sizes and is free of vanishing gradient problem. Furthermore, sentiment analysis is becoming popular in predicting the stock market behavior based on investors reactions. This research work studies the usage of LSTM networks on stock market prediction. Also, assuming that news articles have impact on stock market, this is an attempt to study the relationship between news and stock trend. From the result of the experiment carried out during this research work showed that the financial news do affect the stock market. Sentiment scores from financial news in addition to the stock indices do make the prediction or forecasting process more predictable.

Keywords: Deep neural network, Deep learning, LSTM, Neural Network ,Stock Market, Sentiment Analysis, Time Series.