1. Reduction of the dataset of Baitul Mal aid recipients using the principal component analysis (PCA) method to improve C5.0 algorithm classification results.
- Author
-
Susanti, Evi, Sawaluddin, and Sihombing, Poltak
- Subjects
- *
BANKING industry , *CREDIT analysis , *PRINCIPAL components analysis , *CREDIT risk , *CLASSIFICATION algorithms - Abstract
This research raises problems among Baitul Mal aid recipients regarding aid to micro businesses. The process of assisting is an important activity to develop micro-businesses so that they can continue to operate and develop. Selection is also needed to prevent aid from being distributed incorrectly. Therefore, the proposed solution is to utilize data mining techniques, especially classification methods (clustering) to identify potential aid recipients who truly deserve to receive aid. This research also uses the Principal Component Analysis (PCA) method to reduce attribute dimensions in the dataset to increase the accuracy of the classification process. By optimizing the classification process through appropriate attribute reduction, this research is expected to make a positive contribution to increasing the efficiency and accuracy of credit risk assessment in the banking sector. The results of this research are: accuracy after the dataset has been reduced by 2 (two) attributes has a higher value when compared to the dataset that has not been reduced, this happens because the attribute reduction process is carried out to reduce attributes that are not or less relevant. So it can be said that the reduction process influences the accuracy of the C5.0 algorithm classification results. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF