Location-Aware Web Service QoS Prediction via Deep Collaborative Filtering

Nowadays, there is a large number of web services with similar functions, from which users choose the best according to the quality of service (QoS). Hence, QoS prediction is a primary challenge in service recommendation. Most existing approaches model the user-service interaction relationship. However, the low-dimensional linear and the high-dimensional nonlinear relationships between users and services are seldom considered simultaneously. In addition, although location information, including the local location information of users and services, is incorporated to overcome data sparsity in most approaches. The global location information is seldom considered. Aiming at the above shortcomings, we propose a new QoS prediction model that fuses local and global location information of users and services in the interaction layer of the model. The proposed model uses a multilayer perceptron (MLP) to acquire high-dimensional nonlinear relationships of users and services, where the dot product is employed in complementing the learning of low-dimensional linear relationships. Experimental results on the real world dataset WS-Dream validate the prediction performance of the proposed model.