Long Short Term Memory Network Using Grey Wolf Optimization for Stock Price Prediction

Stock market is backbone of nation's economy. Stable and improving stock market is very important for economy. Stock price prediction is one of the trending topics in data science for researcher. Scientist, analyst, traders are looking for efficient method of prediction of stock price. For profit many investors are keen to know the future of stock market. So, powerful prediction method is required for shareholder. Many methods are implemented using machine learning and deep learning techniques. In this work, we proposed a hybrid framework. This framework consists of Long Short Term Memory Network (LSTM) with a Grey Wolf Optimizer (GWO) which is utilized to estimate stock costs. This proposed framework would improve exactness of prediction of stock cost and helps the investors. We designed traditional LSTM and LSTM with GWO. The results of LSTM with GWO shows better result than LSTM.