In the banking system, banks have a variety of products to provide, but credit lines are their primary source of revenue. As a result, they will profit from the interest earned on the loans they make. Loans, or whether customers repay or default on their loans, affect a bank's profit or loss. The bank's Non-Performing Assets will be reduced by forecasting loan defaulters. As a result, further investigation into this occurrence is essential. Because precise forecasts are essential for benefit maximisation, it's crucial to analyse and compare the various methodologies. The logistic regression model is an important predictive analytics tool for detecting loan defaulters. In order to assess and forecast, data from Kaggle is acquired. Materials and Methods: The dataset needed for the machine learning model for Bank personal loan is acquired from Google’s Kaggle Website. The dataset coloumn have the columns person name ,age, gender, personal loan details, account details and reasons. We analyze, design and implement the infrastructures of the machine learning framework and machine learning application. The dataset are imported and logistic regression algorithm and naive bayes algorithm are tested. The number of groups is 2 for two algorithms the sample size is 75 per group. Results: The results are acquired in the form of accuracy for the inputs provided. The IBM SPSS tool is used in order to obtain the results. from the results we have obtained, the statistical significance difference was observed between the logistic regression algorithm and has an accuracy 70.56%.the naïve bayes algorithm has an accuracy 69.01%,p=0.01 which is more accurate than the value. The independent sample t-test was performed to find the mean, standard deviation, mean statistical significance between the groups. Conclusion: In this paper, based on results we have obtained, the logistic regression Algorithm has more accuracy than Naive Bayes Algorithm