DESIGN AND IMPLEMENTATION OF AN INTERACTIVE WEB-BASED DATA MINING SYSTEM USING KNN, SVM, AND RANDOM FOREST WITH STREAMLIT

Abstract

The rapid growth of digital data requires effective tools to extract meaningful information and support decision-making processes. Data mining and machine learning techniques play an important role in analyzing large datasets and producing accurate classifications. However, implementing machine learning models often requires technical expertise and complex tools. This study aims to design and implement a web-based data mining system using the Streamlit framework integrated with classification algorithms, namely K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Random Forest. The research method includes system design, implementation, and evaluation using three datasets: Iris, Wine, and Digit. The system provides an interactive interface that allows users to select datasets, configure algorithm parameters, evaluate classification accuracy, and visualize results. The implementation results show that all algorithms perform effectively, with Random Forest achieving the highest accuracy, followed by SVM and KNN. The developed system successfully integrates machine learning classification methods into a user-friendly web-based platform, enabling efficient data analysis and visualization. This study demonstrates that interactive web-based data mining systems can enhance accessibility and understanding of machine learning applications for academic and practical use