Machine learning algorithms for vehicle insurance prediction with Random forest and Bayesian approach

The research intends to improve the Machine Learning Algorithms for vehicle insurance prediction: A Bayesian Approach. In order to increase accuracy, two groups in this study compared Random Forest to Naive Bayes. to increase Precision. For the research project, 100 dataset samples were employed, of which 80% were used for training and the remaining 20% for testing. When estimating automobile insurance, 10 N sample sizes were used for each estimate. The Random Forest method enhances accuracy data with 93.605% accuracy compared to Naive Bayes' 82.891% accuracy. P is statistically significant for the prediction of auto insurance, with a significant value of p = e of p = 0.002. The Random Forest method for prediction of vehicle insurance significant improvement over Naive Bayes because of its higher accuracy