Comparative Analysis of Classification of K-Nearest Neighbor (KNN) Algorithm and Decision Tree in Breast Cancer Using Rapidminer

Rosida, Ema
Firmansyah, Andri
Suherman

International Journal of Applied Research and Sustainable Sciences (IJARSS)
Vol. 2 No. 12 (2024): December 2024

Breast cancer is the leading cause of cancer-related deaths among women in Indonesia and worldwide. Early detection is critical for improving survival rates, yet many cases are diagnosed in late stages due to inadequate awareness and diagnostic tools. This study compares the performance of K-Nearest Neighbor (KNN) and Decision Tree algorithms for breast cancer classification using the Wisconsin Breast Cancer dataset. The Cross-Industry Standard Process for Data Mining (CRISP-DM) framework was applied, consisting of Business Understanding, Data Understanding, Data Preparation, Modeling, Evaluation, and Deployment phases. The results indicate that KNN achieved the highest accuracy (97.14%) and Area Under the Curve (AUC) value (0.976), outperforming the Decision Tree algorithm (accuracy: 96.49%, AUC: 0.965). These findings highlight the potential of data mining techniques for enhancing early breast cancer detection and improving clinical decision-making.