Personalized LSTM Based Matrix Factorization for Online QoS Prediction

Quality of Service (QoS) prediction is an important task in services computing, which has been extensively investigated in the past decade. Many time-aware QoS prediction approaches have been proposed and achieved encouraging prediction performance. However, they did not provide effective model updating mechanisms, and thus have to periodically retrain the whole models to deal with the newly coming data. How to timely update the prediction model to precisely predict missing QoS values of candidate services becomes an urgent issue. In this paper, we propose a novel personalized LSTM based matrix factorization approach for online QoS prediction. Our approach can capture the dynamic latent representations of multiple users and services, and the prediction model can be timely updated to deal with the new data. Experiments conducted on a real-world dataset show that our approach outperforms several state-of-the-art approaches in online prediction performance.