IMPLEMENTATION OF XGBOOST AND SUPPORT VECTOR MACHINE FOR BREAST CANCER PREDICTION USING BAYESIAN OPTIMIZATION

Jupron; Fajar Agung  Nugroho

doi:10.30656/rnfpgf88

Authors

Jupron universitas pamulang
Fajar Agung Nugroho Universitas Pamulang

DOI:

https://doi.org/10.30656/rnfpgf88

Abstract

Breast cancer remains one of the most prevalent causes of cancer-related mortality among women worldwide, making early and accurate detection critically important. Machine learning techniques have been widely applied for this purpose; however, many existing studies primarily focus on predictive accuracy without providing comprehensive analysis of model optimization and interpretability. This study proposes a comparative framework integrating Support Vector Machine (SVM) and Extreme Gradient Boosting (XGBoost) with Bayesian Optimization to enhance hyperparameter tuning and model performance. The Breast Cancer Wisconsin Dataset, consisting of 569 samples with 30 numerical features, is used for evaluation. The proposed approach includes data preprocessing, dataset splitting, systematic hyperparameter optimization, model training, and performance evaluation.

Experimental results show that the XGBoost model achieves superior performance compared to SVM, with an accuracy of 98.24% and an Area Under the Curve (AUC) of 0.994. Further analysis indicates that the model maintains a strong balance between precision and recall, with minimal misclassification. In addition, feature importance analysis reveals that attributes related to tumor size and structural irregularities contribute significantly to the prediction results, supporting the interpretability of the model in a medical context. The main contribution of this study lies in providing a more comprehensive evaluation that combines performance comparison, optimization effectiveness, and feature-level interpretation within a unified framework. The findings demonstrate that the integration of XGBoost and Bayesian Optimization offers a reliable and interpretable approach for breast cancer classification, with strong potential for implementation in machine learning–based clinical decision support systems.

Keywords: breast cancer, machine learning, XGBoost, Support Vector Machine, Bayesian Optimization.

References

[1] I. B. Mohammad and M. M. Ahmad, “Bayesian Model Prediction for Breast Cancer Survival: A Retrospective Analysis,” Eur. J. Breast Heal., vol. 21, no. 3, pp. 255–264, 2025.

[2] Z. Rais, S. Muhammad Fahmuddin, Saida, and A. T. Utomo, “Implementation of Machine Learning Algorithm with Extreme Gradient Boosting (XGBoost) Method in Hypertension Level Classification,” J. Appl. Sci. Eng. Technol. Educ., vol. 7, no. 1, pp. 126–136, 2025.

[3] P. Nalela, D. Rao, and P. Rao, “Predicting Survivability of Cancer Patients with Metastatic Patterns Using Explainable AI,” pp. 1–23, 2025.

[4] R. Oktafiani, A. Hermawan, and D. Avianto, “The Effect of Data Split Composition on Breast Cancer Classification Performance Using Machine Learning Algorithms,” Journal of Science and Information, vol. 9, no. April, pp. 19–28, 2023.

[5] I. Solikin, “Data Mining Techniques for Efficient Breast Cancer Prediction,” Fidelity: Journal of Electrical Engineering, vol. 3, no. 3, pp. 63–67, 2021.

[6] L. Widya Astuti, Faradilla, I. Saluza, and M. Fadhiel Alie, “Optimization of Breast Cancer Classification Using Forward Selection in Naive Bayes,” Global Informatics Scientific Journal, vol. 11, no. 2, pp. 63–67, 2020.

[7] M. R. Andryan, M. Fajri, and N. Sulistyowati, “Performance Comparison of XGBoost and Support Vector Machine (SVM) Algorithms for Breast Cancer Diagnosis,” JIKO (Journal of Informatics and Computer Science), vol. 6, no. 1, p. 1, 2022.

[8] N. Nurzilla, “Prediction of Breast Cancer Tumor Growth Using a Machine Learning-Based Linear Regression Model,” Journal of Artificial Intelligence Applications, vol. 1, no. 1, pp. 28–35, 2025.

[9] M. Abdillah et al., “Implementation of XGBoost for Chronic Kidney Disease Classification Using the Chronic Kidney Disease Dataset,” JATISI (Journal of Informatics Engineering and Information Systems), vol. 12, no. 3, 2025.

[10] T. Tinaliah and T. Elizabeth, “Prediction of Breast Cancer Types Using Support Vector Machine Based on Recursive Feature Elimination,” JATISI, vol. 11, no. 3, pp. 1–9, 2024.

[11] Y. N. Kholisho and Z. Amri, “Village Administration System,” JITE (Journal of Informatics and Telecommunication Engineering), vol. 9, no. July, pp. 281–291, 2025.

[12] J. Kusuma, B. H. Hayadi, Wanayumini, and R. Rosnelly, “Comparison of Multi-Layer Perceptron (MLP) and Support Vector Machine (SVM) Methods for Breast Cancer Classification,” MIND (Multimedia Artificial Intelligence Network Database) Journal, vol. 7, no. 1, pp. 51–60, 2022.

[13] R. Resmiati and T. Arifin, “Breast Cancer Patient Classification Using the Support Vector Machine Method with Backward Elimination,” SISTEMASI: Journal of Information Systems, vol. 10, no. 2, pp. 381–393, 2021.

[14] A. Desiani, D. A. Zayanti, I. Ramayanti, F. F. Ramadhan, and G. Giovillando, “Comparison of Support Vector Machine (SVM) and Logistic Regression Algorithms,” Journal of Artificial Intelligence and Information Technology, vol. 4, no. 1, pp. 33–42, 2025.

[15] H. Imaduddin, B. A. Hermansyah, and F. A. Salsabilla B, “Comparison of Support Vector Machine and Decision Tree Methods in Breast Cancer Classification,” Cyberspace: Journal of Information Technology Education, vol. 5, no. 1, p. 22, 2021.

[16] N. Tri, R. Adiningrum, R. Rianti, C. Prianto, T. Informatics, and J. Barat, “Design and Development of a Machine Learning-Based Cancer Prediction Application,” vol. 11, no. 3, 2023.

[17] E. S. Septiany, H. H. Handayani, T. Al Mudzakir, and A. F. N. Masruriyah, “Optimization of the Support Vector Machine Method Using Recursive Feature Elimination and Forward Selection for Breast Cancer Classification,” TIN: Applied Informatics of Nusantara, vol. 5, no. 2, pp. 144–154, 2024.

[18] Z. Syahputra and R. Kurniawan, “High Performance Computing Architecture for Computer Network Systems,” Journal of Computer Networks, Architecture and High Performance Computing, vol. 7, no. 1, pp. 341–352, 2025.