PERBANDINGAN AKURASI ALGORITMA SUPPORT VECTOR MACHINE DAN LOGISTIC REGRESSION DALAM APLIKASI PREDIKSI DIABETES BERBASIS WEB MENGGUNAKAN PYTHON

Ahmad Firmansyah (Universitas PGRI Kanjuruhan Malang)
Amak Yunus (Universitas PGRI Kanjuruhan Malang)
Heri Santoso (Universitas PGRI Kanjuruhan Malang)

BIMASAKTI
Vol 8 No 2 (2026): BIMASAKTI

This study compares the accuracy of the Support Vector Machine (SVM) and Logistic Regression (LR) algorithms in web-based diabetes prediction using Python. The goal is to assess the performance of both algorithms in classifying patient data based on medical parameters. Testing was conducted with a dataset and measuring performance using Accuracy, Precision, Recall, and F1-score. The results showed that SVM obtained Accuracy of 77.27%, Precision of 75.68%, Recall of 51.85%, and F1-score of 61.54%, while Logistic Regression obtained Accuracy of 75.32%, Precision of 64.91%, Recall of 67.27%, and F1-score of 66.07%. SVM was superior in Accuracy and Precision, while Logistic Regression was better in Recall and F1-score. The choice of algorithm depends on the purpose of the application: if the priority is to detect more positive cases, then Logistic Regression is more recommended, while if the focus is to reduce positive prediction errors, SVM is more appropriate. The developed web application makes it easier for users to predict diabetes quickly, helping medical personnel or individuals in early detection and decision making for disease prevention and treatment..