Aim: The objective of the work is to evaluate the accuracy and precision in predicting the rainfall using machine learning algorithms novel tree specific XGBoost (XGB) classification and Logistic Regression (LR) algorithms. Materials and Methods: Novel Tree Specific XGBoost classifier is applied on a weatherAUS dataset that consists of 145461 records. A framework for rainfall prediction machine learning algorithms comparing XGBoost and Logistic Regression classifiers has been proposed and developed. The sample size was measured as 10 per group. Sample size was calculated using clinical analysis, with alpha and beta values 0.05 and 0.5, 95% confidence, pretest power 80% and enrolment ratio 1. The significance value (p) obtained for both accuracy and precision is 0.019, which is less than 0.05. The accuracy and the precision of the classifiers were evaluated and recorded. Results: The machine learning algorithm Logistic Regression classifier produces 79.37% accuracy and 78.00% precision in predicting the rainfall on the dataset used whereas the another machine learning algorithm novel tree specific XGboost classifier predicts the same at the rate of 94.89% accuracy and 94.37% precision. Conclusion: The study proves that novel tree specific XGboost classifier algorithm exhibits better accuracy and precision than Logistic Regression algorithm in rainfall prediction.