<![CDATA[This research aims to analyze the effect of hyperparameter tuning on the performance of Logistic Regression, K-Nearest Neighbours, Support Vector Machine, Decision Tree, Random Forest, Random Forest Classifier, Naive Bayes algorithms. These six algorithms were tested both using hyperparameter tuning and not using hyperparameter tuning. The dataset used in this research is a public dataset, namely the heart datasheet. This datasheet contains information about features related to the diagnosis of heart disease. Hyperparameter tuning is performed using a grid search technique to determine the best combination of hyperparameter values that can improve model accuracy. Performance comparison is done by measuring the accuracy, precision, recall, and F1-score of each algorithm before and after tuning. The research method follows the stages in the Knowledge Discovery in Databases (KDD) methodology. The KDD methodology consists of several stages of data collection, data cleaning to remove errors, data integration from various sources, and data selection and transformation to be ready for analysis. Next, data mining is performed to find patterns or relationships in the data and evaluation and interpretation of the results to ensure their validity. The results show that hyperparameter tuning applied to the six algorithms does not necessarily improve performance. In the algorithm. SVM and decision tree algorithms, the performance results before hyperparameter tuning actually have a higher accuracy value. The performance of algorithms that experienced an increase after hyperparameter tuning was logistic regression and K-Nearest neighbours. The same performance results are generated in the Random Forest and Naive Bayes algorithms. Based on testing the six algorithms and using the heart datasheet, the hyperparameter tuning process does not always result in a better performance value.]]>
Copyrights © 2025
