A SEMI-SUPERVISED LEARNING APPROACH TO QUALITY-BASED WEB SERVICE CLASSIFICATION

ABSTRACT

The "Web Service Classification and Recommendation" project aims to enhance the process of selecting and recommending web services using machine learning techniques. The project is divided into two primary components: Classification Model: This model classifies web services into quality categories—Bronze, Silver, Gold, and Platinum—based on key Quality of Service (QoS) attributes like response time, availability, reliability, and throughput. The model is built using several machine learning algorithms, including Decision Trees, Support Vector Machines (SVM), Logistic Regression, K-Nearest Neighbors (KNN), Naive Bayes, Random Forest, Multi-Layer Perceptrons (MLP), and XGBoost. Additionally, Explainable AI (LIME) is employed to provide transparency and interpretability in the classification decisions, allowing users to understand why a web service falls into a particular quality category. Recommendation Model: Using the K-Nearest Neighbors (KNN) algorithm, this model recommends the top 10 most relevant web services based on user-inputted QoS attributes. It computes the similarity between the input data and existing web services to provide tailored recommendations. The system's user-friendly interface allows users to upload web service data, view classification results, and receive personalized recommendations. The project provides an efficient and scalable solution for selecting high-quality web services, enabling users to make data-driven decisions based on performance metrics. With its dual approach—classification and recommendation—this system improves decision-making, enhances user experience, and supports businesses in optimizing service selection.