Support Vector Machine Performance In Diabetes Data Classification With GridsearchCV Optimization

I Wayan Adi Sparta; Putu Eka Parianthana

Authors

I Wayan Adi Sparta Prodi Sistem Informasi, Fakultas Teknologi dan Ilmu Kesehatan, Universitas Bali Dwipa
Putu Eka Parianthana Prodi Sistem Informasi, Fakultas Teknologi dan Ilmu Kesehatan, Universitas Bali Dwipa

Keywords:

Support Vector Machine, Diabetes, Classification, Machine Learning, Parameter Optimization

Abstract

Diabetes is one of the most common chronic diseases and has the potential to cause serious complications if not detected early. This study evaluates the performance of the Support Vector Machine (SVM) algorithm in diabetes data classification using parameter optimization with GridSearchCV. The dataset used includes eight health features from Kaggle, which include factors such as glucose levels, blood pressure, and body mass index (BMI). After parameter optimization, the SVM model achieved 74% accuracy on the test data, with precision and recall performance varying between classes. This research highlights the importance of hyperparameter optimization in improving the accuracy and balance of health data classification. These results provide insight into the application of machine learning technologies to support early detection and medical decision-making.

Downloads

Download data is not yet available.

References

Afifuddin, A., & Hakim, L. (2023). Deteksi Penyakit Diabetes Mellitus Menggunakan Algoritma Decision Tree Model Arsitektur C4. 5. Jurnal Krisnadana, 3(1), 25–33.

Aini, W. R., Sudipa, I. G. I., Sandana, I. P. D., Putra, D. M. D. U., & Indrawan, I. G. A. (2024). IDENTIFYING FAKE ACCOUNTS IN SOCIAL MEDIA COMMERCIAL VIDEOS USING SUPPORT VECTOR MACHINE METHOD. Proceeding International Conference on Information Technology, Multimedia, Architecture, Design, and E-Business, 3, 79–86.

Hidayatulloh, F., Andika, I. G., Suryawan, I. W. D., Ariantini, M. S., & Sudipa, I. G. I. (2024). Analisis Sentimen Opini Publik Terhadap Konser Coldplay Di Jakarta Pada Twitter Menggunakan Metode Support Vector Machine. INFORMAL: Informatics Journal, 9(2), 137–144.

Ishlah, A. W., Sudarno, S., & Kartikasari, P. (2023). IMPLEMENTASI GRIDSEARCHCV PADA SUPPORT VECTOR REGRESSION (SVR) UNTUK PERAMALAN HARGA SAHAM. Jurnal Gaussian, 12(2), 276–286. https://doi.org/10.14710/j.gauss.12.2.276-286

Khadangi, E., & Bagheri, A. (2013). Comparing MLP, SVM and KNN for predicting trust between users in Facebook. Proceedings of the 3rd International Conference on Computer and Knowledge Engineering, ICCKE 2013, Iccke, 466–470. https://doi.org/10.1109/ICCKE.2013.6682864

Khan, A., Khan, A., Khan, M. M., Farid, K., Alam, M. M., & Su’ud, M. B. M. (2022). Cardiovascular and Diabetes Diseases Classification Using Ensemble Stacking Classifiers With SVM as a Meta Classifier. Diagnostics, 12(11), 2595. https://doi.org/10.3390/diagnostics12112595

Lin, A. K. (2024). The AI Revolution in Financial Services: Emerging Methods for Fraud Detection and Prevention. Jurnal Galaksi, 1(1), 43–51. https://doi.org/10.70103/galaksi.v1i1.5

Purbolaksono, M. D., Irvan Tantowi, M., Imam Hidayat, A., & Adiwijaya, A. (2021). Perbandingan Support Vector Machine dan Modified Balanced Random Forest dalam Deteksi Pasien Penyakit Diabetes. Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi), 5(2), 393–399. https://doi.org/10.29207/resti.v5i2.3008

Suryawan, I. G. T., Pratiwi, N. L. S., Sudipa, I. G. I., & Anandita, I. B. G. (2024). Performance of Moving Average and Exponential Smoothing Methods in Forecasting Demand for Blood Components. ISAR Journal of Science and Technology, 2(11), 7–17. https://doi.org/10.5281/zenodo.14250561

Valero-Carreras, D., Alcaraz, J., & Landete, M. (2023). Comparing two SVM models through different metrics based on the confusion matrix. Computers & Operations Research, 152, 106131.