Optimized Machine Learning Models for Diabetes Prediction- Hyperparameter Tuned Comparative Study

Abstract

Translate Article

In order to forecast diabetes, this study uses a variety of machine learning methods using the PIMA Indians Diabetes Dataset. Hyperparameter tuning is applied to six algorithms in this study: Naïve Bayes, Random Forest, Decision Tree, K-Nearest Neighbors (KNN), and Logistic Regression. Data pre-processing, feature engineering, exploratory data analysis (EDA), and model training are all steps in the process. Accuracy, precision, recall, and F1-score are used to assess the models' performance. With 99% accuracy, Random Forest emerged as the best model, indicating significant potential for use in practical medical diagnosis. The study's key findings are outlined in the concluding remarks, which also offer ideas for future research topics.