Stock Price Prediction of Nepal using LSTM
Abstract- Predicting behavior of Stock Market is a challenging task. It is a trending topic in machine learning. It assists the investor to minimize the risk and fluctuation in Stock Market. The most popular model for RNN(Recurrent Neural Network) right now is the LSTM (Long Short-Term Memory) network, which is made into use for deep learning because through it, very large architectures can be successfully trained.
In this paper, through the use of LSTM, prediction is done for determining the future stock market value. Stock data of ten different companies from different sectors that are currently running in Nepal were extracted from targeted website ‘sharesansar.com’. The opening price, closing price, high and low were taken into consideration for analysis. Evaluation of the model is performed by determining the root mean square error between the predicted values and the test values. The accuracy was found to be approximately 80%.
Keywords—Stock Market, Long Short-Term Memory, Machine Learning Algorithms, NEPSE Index