Skripsi
KLASIFIKASI TINGKAT RISIKO KREDIT MENGGUNAKAN METODE NAIVE BAYES DAN FUZZY NAIVE BAYES DENGAN TEKNIK K-FOLD CROSS VALIDATION
Credit is a condition of delivery in the form of goods, money or services from the first party (credit giver) to another party (credit recipient) with a joint agreement to be completed within a certain period of time in return for the additional principal. Customers who apply for credit must meet the conditions set by the bank with the aim of avoiding unexpected possibilities such as bad credit. In preventing bad credit, it is necessary to make the right decision to accept or reject credit applications. Therefore, this research was conducted with the aim of classifying credit risk levels using the naïve Bayes and fuzzy naïve Bayes methods. However, in the use of naïve Bayes and fuzzy naïve Bayes methods, there are often ups and downs in accuracy, so validation techniques are needed to measure model performance. In this study, the k-fold cross validation technique will be used to obtain the model with the best accuracy. The data used is the UCI Credit Card Approval Dataset Repository, totaling 30,000 data. Classification using the naïve Bayes method produces an average value of accuracy, precision, recall and f-score of 79.85%, 70.34%, 15.41%, 5.24%, respectively. Classification using the fuzzy naïve Bayes method produces an average value of accuracy, precision, recall and f-score of 80.23%, 62.22%, 26.72%, 37.32%, respectively. The results showed that the fuzzy naïve Bayes method has a better level of classification accuracy than the naïve Bayes method as seen from the average accuracy, recall and f-score. However, the naïve Bayes method has better precision than the naïve Bayes fuzzy method.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2307002220 | T107515 | T1075152023 | Central Library (Referens) | Available but not for loan - Not for Loan |
No other version available