Web service recommendation based on time‐aware users clustering and multi‐valued QoS prediction

Abstract

Summary With the growing number of functionally similar services over the Internet, recommendation techniques become a natural choice to cope with the challenging task of optimal service selection, and to help consumers satisfy their needs and preferences. However, most existing models on service recommendation are static, while in the real world, the perception and popularity of Web services may continually change. Time is becoming an increasingly important factor in recommender systems since time effects influence users' preferences to a large extent. In order to help users with this problem, we propose a time‐aware Web service recommendation system. First, we use K‐means clustering method in order to exclude the less similar users, which share few common Web services with the active user at different times. Slope One algorithm is also adopted in order to deal with data sparsity problem by predicting the missing ratings over time. Then, a recommendation algorithm is presented in order to recommend the top‐rated Web services. Experiments proved the accuracy of our approach compared to five existing solutions.

An advancing method for web service reliability and scalability using ResNet convolution neural network optimized with Zebra Optimization Algorithm

“…Using the Zero Optimization Algorithm (ZOA) is to improve the weight parameters of the ResNetCNN model. 21 This indicates that existing methods may not employ advanced optimization techniques to fine-tune their models for better predictions. The main contribution of the article is given below:…”

“…Accurately assessing these aspects in web service compositions is challenging, as it requires considering both the individual services and their interactions within the composition. Using the Zero Optimization Algorithm (ZOA) is to improve the weight parameters of the ResNetCNN model 21 . This indicates that existing methods may not employ advanced optimization techniques to fine‐tune their models for better predictions.…”

A new model for trustworthy web service QoS prediction

“…20 Following that, many studies used CF-based prediction methods to determine the QoS values of the web services. 18,[20][21][22][23] In recent years, QoS prediction has been known as the best method to determine the missed QoS values of web services, and it has become one of the attractive topics in the web service domain.…”