In this research, the primary analysis method is the Naive Bayes Classifier for predicting the reliability of loan repayment in cooperative environments to facilitate credit analysis for a cooperative’s staff. Floor management which means how employees conduct assessments of loans can lead to the formation of non-performing loans as borrowers fail to pay as agreed. To avoid these risks the following evaluation procedures in disbursement of loans are highly relevant and necessary. Thus, drawing on historical member data, this research uses data mining, namely the Naive Bayes Classifier, to predict the chances of smooth loan repayment. The Naive Bayes method is based on the records of various attributes of the members, which include occupation, income, home ownership, amount of loan, and type of loan. These attributes are useful in the prediction of some of the qualities that are useful in decision-making in as much as the loan is concerned. Based on the assessment of the Naive Bayes classifier on the current model, an accuracy rate of 90% was obtained. 00%, an accuracy of 0. 880%, and a recall (Sensitivity) of 83%. , a recall of 33%, and the precision of 100%. These measures indicate the high performance of the proposed model in correctly classifying positive as well as negative loan repayment status. In the subsequent studies, it will be interesting to work on expanding a more appropriate dataset for improving the model’s predictive capability by increasing the variation of individuals’ examples. Hence, the expansion of more intricate computing approaches that consider attributes’ interdependencies may shed light on enhanced methods of risk identification and loan approvals. Through progressive enhancement and creativity in the lending area of operations, the risks involved in lending as well as the overall loaning practices can be controlled and enhanced respectively.

Prediction Smoothness of Installment Payments Data Mining Naive Bayes Classifier Machine Learning.