Time-Aware QoS Prediction for Cloud Service Recommendation Based on Matrix Factorization

Abstract

Prediction of quality of service (QoS) is a critical area of research for cloud service recommendation. The disadvantage of QoS values is that they are directly related to time series of service status and network condition and thus instantly vary over time. The main contribution of this paper is to consider service invocation time as a dynamic factor in the collaborative filtering model and recommend high-quality services for target user. In particular, this paper proposes a time-aware matrix factorization (TMF) model that integrates QoS time series to provide two-phase QoS predictions for cloud service recommendation. The TMF model uses an adaptive matrix factorization model on a sparse QoS dataset to predict the missing QoS values. A temporal smoothing method is then developed and applied to the predicted result to perform the time-varying QoS prediction that accounts for the dependence of QoS values at different time intervals. The numerical experiments presented are conducted to validate the accuracy of the proposed method on a public QoS dataset.