Prediction of Indian government stakeholder oil stock prices using hyper parameterized LSTM models

Abstract

An investment is capturing money to profit from it. Investing has become a buzzword among middle-class households. People can invest their money in a variety of ways. Land, gold, jewels, cash, mutual funds, and the stock market may all make investments. We all know how volatile the stock market is. But why is it beneficial to middle-class families? For example, a man from a middle-class family may want to buy land, but it may be too expensive. However, it is possible to obtain a share for a pittance. The disparity between investment and result is apparent here. Forecasting is challenging due to the volatility and non-linearity of financial stock markets. Artificial intelligence and increased computing power have enhanced accuracy in stock price prediction programs. In this paper, we consider Bharat Petroleum Corporation Limited (BPCL), Hindustan Petroleum Corporation Limited (HPCL), and Indian Oil Corporation (I.O.C.) to be the government oil corporations with the most significant stake in the Indian petroleum industry. This paper enhances the prediction of effect by combining a hybridized model of Machine Learning with a Data Science model. Machine Learning-based Hyper Parameter Tuning of Neural Network LSTM has been used to estimate the following day closing price for three equity from Indian government oil industries. The open and close stock prices are considered when creating new model input variables. This project's accuracy is around 99 percent.