Stock Price Prediction Using Machine Learning algorithm with Web Interface (GUI)

Abstract

Predicting the stock market trend is difficult due to the stock market’s high level of uncertainty. Many approaches for stock price and market prediction have been developed in the past. Different algorithms such as Long Short-Term Memory (LSTM), Support Vector Machine (SVM), Linear regression, and Decision trees are utilized in this study to forecast the future closing price of stocks for a specific firm. In this paper, the accuracy of these mentioned algorithms is also being compared. A seven-day study is also performed, illustrating the actual and anticipated closing prices for two companies using different algorithms. The outcome of the previous forecast is compared to the other algorithms, and a final algorithm is chosen based on it. A final model is created by taking many technical parameters in consideration in order to have more precise anticipated the price. Based on the final model, a 10-days examination of the actual and anticipated closing prices for ten different firms is also performed. Finally, A web application-based Graphical User Interface (GUI) was built using the Stream-lit library. The GUI includes features such as a forecast graph, a graph for historical data, and a company selection as well as the start and the end date.