Design of Intraday Stock Price Prediction Model Using Machine Learning via Technical Indicators

Predicting the direction of stocks is an important task for all investors to gain a desirable profit. Stock market prediction is very important since it allows investors to make profitable decisions about when to buy and sell stocks, which ultimately result in accurate price prediction of stocks. Stock price prediction using technical data analysis results in better results than the other prediction models. This work uses the Logistic Regression algorithm for Intraday Stock Prediction to predict the close price of the next day based on technical indicators. The metrics such as Accuracy, Mean Squared Error (MSE) and Root Mean Square Error (RMSE) are used to evaluate the model’s performance. The experiment is conducted on stocks that are traded globally. When compared to other machine learning (ML) models, the experimental results demonstrate that the suggested model performed better in terms of low MSE, RMSE, and high accuracy as well as in predicting close price on real data. In the future, rather than focusing only on the stock’s close price, the researchers can explore many different technical indicators to predict the high, open and low price of the stock.