A Novel APP Recommendation Method Based on SVD and Social Influence

Abstract

The market for Mobile Applications APP for short is perhaps the most thriving sector nowadays in the software industry with about 4 million APPs around the world. APP recommendation is playing an increasingly important role in every APP store to enhance user experience and raise revenue. Existing recommendation strategies are mainly based on user's individual information while their social relations are often neglected. However, it is an intuitive knowledge that users tend to be affected by their friends' recommendation in the choice of APPs. Therefore, it is worth investigating whether and how social influence can be employed for APP recommendation. In this paper, to answer the above question, we propose a novel APP recommendation method based on SVD Singular Value Decomposition algorithm and social influence which is defined by an extended CD Credit Distribution model. The experimental results based on the real-world datasets from Tencent APP Store demonstrate that our proposed method with social influence can achieve a better recommendation results than conventional SVD based algorithm without social relations.