Integration of Adasyn Method with Decision Tree Algorithm in Handling Imbalance Class for Loan Status Prediction

Abstract

Determining the provision of credit is generally carried out based on measuring credibility using credit analysis principles (5C principles). However, this method requires quite a long processing time and is very susceptible to subjective judgments which might influence the final results. This research uses data mining techniques by developing modeling on loan status prediction datasets. The stages in this research include data preprocessing, modeling, and evaluation using accuracy metrics and ROC graphs. In this analysis, it is known that there is a class imbalance in the processed dataset, so an oversampling technique must be carried out. This research uses the ADASYN (Adaptive Synthetic) Oversampling technique to ensure the class distribution is more balanced. Then, the ADASYN technique is integrated with the Decision Tree Algorithm to build a prediction model. The research results show that the two methods can increase prediction accuracy by 12.22%, from 73,91% to 85.22%. This improvement was obtained by comparing the accuracy results before and after using the ADASYN Oversampling technique. This finding is important because it proves that implementing such integration modeling can significantly improve the performance of classification models and provide strong potential for practical application in helping more effective loan status predictions.

Keywords

• adasyn
• decision tree
• imbalance class
• loans
• oversampling techniques