Development of an automated machine learning (automl) system and web interface

Machine learning is part of our everyday lives today. It can be seen in many areas of life. Machine learning increases efficiency, eliminates manual adjustments, and includes applications that shorten processing time. The developed web-based interface automatically runs multiple methods in the background to provide users with the most appropriate results. A flexible structure has been established to shorten the analysis time. The developed system is designed using Python's scikit-learn and Streamlit libraries and has a layered architecture consisting of a user interface, business logic, and data processing layers. Separate wrapper systems have been written for all scikit-learn models and tools. The system supports basic machine learning tasks such as 15 different classification, 15 different regression, and 8 different clustering algorithms. Additionally, it offers comprehensive data preprocessing (scaling, missing data imputation, encoding, feature engineering, feature selection, data sampling, PCA), model comparison, hyperparameter optimization (with Optuna integration), session management, and detailed visualization capabilities. The developed system has been tested on various synthetic datasets for classification, regression, and clustering tasks. This work enables users from different fields of expertise to apply, evaluate, and compare the performance of machine learning algorithms on datasets without requiring coding knowledge.