This research endeavour includes a comparison analysis of several regression models to anticipate the depth and extent of a certain phenomenon in earthquake. Emphasizing the importance of earthquake prediction in various applications, the investigation meticulously assesses the models using correlation analysis, iterative feature removal, and model training analysis to improve precision. Regression methods such as random forest regression (RFR), decision tree regression, gradient boosting regression, support vector regression (SVR), neural network regression, KNN regression, ridge regression, lasso regression, elastic net regression, and LGBM regression are applied. The purpose of the research is to identify the most accurate model for the anticipation of depth and magnitude of the earthquake. The study process includes data preparation, feature selection, and model training on a suitable dataset. Performance evaluation metrics such as mean squared error, mean absolute error, and R-squared are used to measure the prediction abilities of the models. The study’s findings provide useful insights into the strengths and shortcomings of each model, assisting in determining the optimum technique for depth and magnitude prediction in this unique scenario. Results showcase the superior performance of SVR in earthquake depth prediction and RFR in magnitude prediction.