Stock Market Trend Prediction Along with Twitter Sentiment Analysis

Abstract

The Stock Market Prediction and Analysis has always been one of the most challenging tasks (Polamuri and Mohan in A survey on stock market prediction using machine learning techniques, 2019; Parmar et al. in First international conference on secure cyber computing and communication (ICSCCC), pp. 574–576, 2018). The variety of influences and unpredictability beats even the heavyweights to ground when it comes to successfully analyzing Stock Price data. In the proposed System, we have designed and successfully built a Machine Learning model using Long-Short Term Memory (LSTM) algorithm which helps for prediction of stock price data. We have done experimentations for better training, accuracy and results, on used data. The proposed system is also deployed on a web application which helps eliminate/reduce the difficulty of its use for the users. The model also works on the real-time data as we are using Yahoo finance API for getting updated data for model training and prediction. Lastly, The Indian stock market prices are also heavily driven by public sentiments which have for providing a better public opinion upon a particular stock. To help our users tackle this, we have added twitter sentiment analysis as a feature which provides us results in term of percentages of positive and negative sentiments within the tweets in the public domain at present about a particular stock, achieving a better opinion on a particular stock for the users. The resulting model successfully gives us a prediction graphs as an output when given a particular stock on the proposed web application. We obtained least error in prediction, for Asian Paints data for the split of 80:20, using 75 epochs.