This paper explores contemporary supervised learning models that utilize machine learning algorithms for predicting rainfall in India. Given the global significance of rainfall and its impact on crucial human-dependent factors, accurate prediction remains a challenging task. In this study, various decision models, including XGBoost, CatBoost, Light GBM, Random Forest, Neural Network, Decision Tree, and Logistic Regression have been employed, to analyze Indian rainfall data. The objective is to compare the effectiveness of these classifiers and achieve optimized results in terms of time and accuracy for rainfall predictions. It has been observed that different rainfall prediction models provide an accuracy with execution time in the range of 10–90%. The Decision Tree model provides optimized results in terms of accuracy and execution time for the dataset used.