This research paper aims to investigate the impact of using the Synthetic Minority Over-Sampling Technique (SMOTE) on the performance of several machine learning algorithms on imbalanced dataset. Imbalanced datasets are a common problem in many real-world applications, where one class is much more prevalent than the other class. This imbalance can lead to biased models, where the majority class dominates the model's predictions, and the minority class is often misclassified. To address this problem, we applied the SMOTE algorithm to generate synthetic data for the minority class. We evaluated the performance of several popular machine learning algorithms including logistic regression, decision trees, ensemble learning, support vector machines, Neural networks and Auto ML approach on both the original imbalanced dataset and the SMOTE-augmented dataset. The experimental results demonstrate that using SMOTE significantly improves the accuracy of the machine learning algorithms on imbalanced datasets. In conclusion, our research highlights the importance of considering the impact of imbalanced datasets on machine learning algorithm’s performance and demonstrates the effectiveness of SMOTE in addressing this issue. Our results can be useful to practitioners working on imbalanced datasets to choose an appropriate machine-learning algorithm and to decide whether to use SMOTE to improve their model’s performance.