SPDL-Stock Price Prediction with Deep Learning

Stock market variation data is collected in the form of breaking news from various business websites. The stock market trend changes with key financial reforms, weather conditions, and political events. The dataset is created using financial news text data. The dataset features consist of TF-IDF of various companies of Bombay Stock Exchange (BSE) along with open, high, low price parameters for prediction. Research considers the next day's stock price prediction using a deep learning framework (SPDL). The data set is transformed by various deep learning techniques to get more accurate results. The proposed model produces approximately 85 % of accurate predictions with a deep learning framework. The market trends in terms of high and low stock values are matching exactly. The research work is converted to Shiny Application (SPruH). Google analytics is used to analyze the usage of an application. The results can be improved with the use of high-frequency trading algorithms in the future.