Validate students performance based on enrolled module using classification technique of novel naive bayes comparing with logistic regression

The project’s goal is to forecast pupils’ success based on evaluations. The sample space was generated using a sample size calculator, and two machine learning algorithms— We used logistic regression with a sample size of 10, and naive bayes with a sample size of 10. The suggested approach uses Naive Bayes to categorise student performance. The Naive Bayes findings are contrasted using the logistic regression algorithm. Based on the kids’ arithmetic, reading, and writing scores, comparisons are made regarding their performance. The accuracy of the logistic regression approach is lower (79.40%). compared to Naive Bayes (93.40%). A two-tailed t-test revealed comparing the Naive Bayes and Logistic Regression for statistical significance with a p value of 0.001 (p0.05). Predicting the students performance significantly seems to be better in the Novel Naive Bayes than Logistic regression.