Location-based deep factorization machine model for service recommendation

The era of everythingasaservice led to an explosion of services with similar functionalities on the internet. Quickly obtaining a high-quality service has become a research focus in the field of service recommendation. Studies show that quality of service (QoS) predictions are an effective way to discover services with high quality. However, sparse data and performance fluctuation challenge the accuracy and robustness of QoS prediction. To solve these two challenges, this paper proposes a location-based deep factorization machine model, namely LDFM, by employing information entropy and location projection of users and services. Particularly, our LDFM can be decomposed into three phases: i) extending a raw QoS dataset without introducing additional information, where LDFM projects the existing users (services) in the direction of their position vectors to increase the number of users (services) as well as the number of records that users invoke services; ii) mining a sufficient number of potential features behind the behaviors of users who invoke services, where LDFM employs a factorization machine to extract potential features of breadth with low dimensions (i.e., one and two dimensions) and utilizes deep learning to seek potential depth features with high dimensions; and iii) weighting extracted features within various dimensions, where LDFM employs information entropy to strengthen the positive effects of valid features while reducing the negative impacts generated by biased features. Our experimental results (including t-test analyses) show that our proposed LDFM always performs well under different user-service matrix densities and performs better than existing start-of-the-art methods in terms of the accuracy and robustness of QoS predictions.