Comparative Analysis of Accuracy For Predicting Earthquake Occurrence Using Linear Regression Over Poisson Regression

In the context of earthquake prediction, the purpose of this study is to evaluate the accuracy of the Linear Regression Algorithm in comparison to Poisson regression. The linear regression method and the Poisson regression are the two classes that are included in this study. Each group has a sample size of ten, and the sample size is iterated and calculated using clinical software with an alpha value of 0.05, a G-power pre-test score of 80%, and a confidence interval of 95%. It was Kaggle.com that provided the earthquake dataset that contained 10112 samples for the purpose of this investigation. The accuracy of the novel linear regression algorithm is 89.50%, which indicates that it is superior to Poisson regression, which has a value of 77.60%. Furthermore, the results demonstrate that there is a significant difference between Linear regression and Poisson regression, with a value of p=0.000 (Independent sample t-test p<0.05) in the prediction of earthquakes using SPSS statistical analysis. According to the findings of this research, the Linear Regression Algorithm does a better job at predicting earthquakes than the Poisson regression methodology