General Regression Neural Networks Based On Stock Prediction

Abstract

In an unclear financial market, it's hard to guess what the price of a stock will be. Financial professionals and academics equally utilise statistical, economic, and neural network theories to make investments and gain market insights. In this study, we evaluate the performance of five prominent neural network models—back propagation (BP), radial basis function (RBF), general regression neural network (GRNN), and support vector machine regression (SVMR)—by assessing their ability to make accurate predictions. ARIMA and LSTM have been utilised to forecast the stock market, but more precise models may be possible. In this study, stock price forecasts are generated utilising neural networks and other methods.