<![CDATA[As a non-bank financial institution, a guarantee company provides credit guarantees to individuals, government institutions, and/or business entities that are feasible in terms of business and business but do not yet meet banking requirements and are not creditworthy (feasible but not yet bankable). This guarantee activity involves three parties, namely the Guarantee Recipient, the Guaranteed, and the Guarantor. Credit assessment in this guarantee company is important to help MSMEs in obtaining financing from banks even though they are not yet bankable. This study aims to determine, measure accuracy and determine what factors influence the application of the Naïve Bayes Classifier in a digital strategy to classify which debtor criteria are eligible and unfit for Credit Guarantee. The categorization of the guarantee data variables used are work area, business sector, credit period, credit allocation, guaranteed age, and credit ceiling value. To achieve the objectives of this study, a digital strategy system is needed that utilizes machine learning to be able to classify guarantee data to determine which debtor criteria are eligible and unfit for Credit Guarantee. The Naïve Bayes Classifier method was chosen because of its simple and fast nature in classifying data but is effective in making predictions based on probability..]]>
Copyrights © 2025
