<![CDATA[Consumer product purchases often rely on credit as a solution to finance the acquisition, including for electronic and furniture products. It's not just consumers involved in credit use; manufacturers and distributors of electronic and furniture products also depend on credit facilities to support sales. Predicting credit eligibility directly impacts credit providers' decisions in assessing whether a consumer qualifies for credit to purchase those products or not. Through accurate credit eligibility assessments, credit providers can mitigate credit risks associated with extending credit to consumers who may have lower repayment capabilities. Naive bayes, as an analytical method, offers ease of implementation, effectiveness in managing categorical data, the ability to compare probabilities, good accuracy, easily interpretable results, and the capability to handle categorical variables with numerous values. The utilization of naive bayes classification methods in predicting loan eligibility for customers in this study resulted in data accuracy metrics of 90%, recall of 80%, and precision of 100%. Additionally, the AUC value produced is 1.000.]]>
Copyrights © 2023
