Exploration Of Recommendation System for Service Discovery

Abstract

The Service discovery platforms have gained significant importance in connecting users with service providers. However, recommending relevant services tailored to individual user preferences remains a challenging problem. This study explores the application of machine learning algorithms to develop an effective recommendation system for service discovery. A comparative analysis of algorithms, including Logistic Regression, K-Nearest Neighbors (KNN), Decision Trees, Random Forest, and Gradient Boosting, was performed. Results demonstrate that Logistic Regression achieves optimal performance in terms of accuracy, interpretability, and scalability for real-time applications, making it the most suitable choice for the platform. Future directions include incorporating hybrid recommendation techniques for further enhancement.