The task of choosing a suitable web service has become increasingly difficult in today’s landscape due to the growing number of services offering similar functionalities. This paper addresses the critical need for efficient web service selection based on Quality of Service parameters. A minimal set of discrete QoS characteristics were carefully chosen as inputs for several machine learning models targeted at finding and suggesting suitable web services. The performance of these models is systematically evaluated and compared. The machine learning techniques used for this work include a Support Vector Machine, Decision Tree, and Random Forest. Among these, the results show that the proposed Random Forest model consistently outperforms other techniques in terms of accuracy and effectiveness. This study contributes to the advancement of web service selection methodologies by providing insights into the comparative performance of various machine learning approaches, ultimately offering a valuable guide for decision-makers in navigating the intricate landscape of web service options.