Forecasting of Rainfall Using Novel SVM and Compare Prediction Accuracy with Logistic Regression Algorithm

Utilizing a novel super vector machine algorithm to forecast rainfall efficiency and comparing the accuracy of the predictions with a logistic regression algorithm. Using machine learning algorithms, such as the novel super vector machine algorithm and the logistic regression algorithm, to predict the amount of rain (Chang, Hsu, and Chang 2019). In this case, the sample size for the two groups is 20, and the pretest power analysis was performed at an 80% level. The software used was Novel Super Vector Machine, which had an accuracy of 94.0%, and Logistic Regression, which had an accuracy of 90.55Here is a statistical difference in accuracy for two algorithms is p=0.908 (<tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$p$</tex> < 0.05) by performing independent sample t-tests so the results show that the group are statistically insignificant. Novel Super Vector Machine Algorithm of Accuracy 89.93% Performs better than the Logistic Regression Algorithm of Accuracy 86.02%.