Abstract

An investor always moves forward with well-thought-out plans that, over time, maximize earnings. The share market is where most investments are made globally. Investments in the share market carry risk, therefore investors must choose when it is best to make their decisions. Prior to investing, a significant amount of forecasting and computation is required. Using an engine that forecasts corporate share prices is crucial for making well-informed investing decisions and creating tangible financial strategies for investors. It has been suggested that the engine use suggested machine learning techniques to predict future corporate share values of corporations. The application models forecast a dependable and significant share price by incorporating market indicators, sentiment research, and previous financial data on share price. The comprehensive model's mission is to identify a significant share price for the company by using machine learning methods to forecast future share prices of companies with a high degree of dependability. The yfinance library, which gives users access to a substantial database of stock market data, is utilized by the model. This information is gathered from prior financial data in order to construct the model. Past share prices, trading activity, and other significant market indexes are included in this data. After that, the data is pre-processed to address disparities that can reduce the prediction model's precision. SVR, random forests, and LSTM machine learning systems were used in the construction of the models. After the models are trained on the prepared dataset, their performance is evaluated using appropriate metrics such as accuracy or mean squared error. Cross-validation techniques are employed to ensure the robustness of the models and prevent overfitting. To validate the model, the outcomes are compared with the share prices of the current day and the day before