Stock Price Prediction Using LSTM, ARIMA and UCM

Abstract : The stock market is growing abundantly due to the rise of investors for their passive income is This article aims to develop an innovative artificial recurrent neural network approach for better stock market forecasts. The stock 611market is receiving a lot of attention from investors. Capturing the regularity of stock market changes has always been a key point for investors and investment firms. Investors are very interested in the field of stock price forecasting research. To make a successful investment, many investors want to know the future of the stock market. The data is pulled from the livestock market for analysis and visualization and results in analysis in real-time and offline. Predictive methods can be divided into two broad categories: statistical methods and artificial intelligence methods. Statistical methods include the logistic regression model and ARIMA, UCM model. Artificial intelligence techniques include multi-layer perceptron’s, accumulative neural networks, Naïve Bayes, back-propagation networks, single-layer LSTMs, vector bearers, cyclic neural networks, and more. From this research, LSTM is achieving less Error percentage than any other model. LSTM helps investors, analysts, or anyone interested in investing in the stock market to get a better understanding of the future state of the stock market.