Intraday trading refers to the buying and selling of equities inside the same trading day. Day traders have a decent chance of generating money whether the market is going up or down. Stock market decisions are increasingly aided by computers and algorithms. Concerns the profitability of algorithmic trading in stocks have been raised. Can machines be taught to beat the market? Is it feasible for a program to choose actions that maximize profit? Is it possible to reduce investing risk using mathematical formulas? Our research aims to provide explanations for some of these mysteries. We present a machine learning and deep learning-based trading system for day trading. To anticipate the markets’ behavior on the following trading day, we first extracted the relevant features from the raw data and used machine and deep learning algorithms such as Artificial Neural Network [ANN], Decision Tree [DT], Support Vector Machine [SVM], Logistic Regression [LR], and Random Forest Classifier [RF]. After that, we employ a majority vote from all of the classifiers to reach a conclusion. When used to a predictive modelling problem, ensembles are used to boost the performance of individual predictive models.