Prediction of purchase behaviors across heterogeneous social networks

Abstract

Due to the development of web services, many social network sites, as well as online shopping sites have been booming in the past decade, where it is a common phenomenon that people are likely to use multiple services at the same time. On the one hand, previous research findings indicate the data sparsity issues of online shopping accounts, which is caused by the heavy-tailed distribution of user information. On the other hand, in social network sites, the personal information and the corresponding statuses of an account are abundant, and their genuineness is guaranteed either by the service provider, or by the willingness of the account owner to connect to his or her friends in reality. Making use of the correlation between accounts of a same individual is a crucial prerequisite for many interesting cross network applications, such as improving the recommendation performance of the online shopping sites using extra information from social network services. In this paper, we firstly propose a game-theoretic method to identify correlation accounts of individuals between social network sites and online shopping sites with stable matching model, incorporating account profiles as well as historical behaviors. Using the above account relationships, we then put forward a predicting method that combines heterogeneous social network information and online shopping information, to predict the purchasing behaviors. The results show that our method identifies up to 70 % of the correlation accounts between Facebook and eBay, one of the most popular social network sites and online shopping 123Prediction of purchase behaviors across heterogeneous... 3321 sites in the world, respectively. The experimental results also show that using the correlation account sets, the accuracy of our purchase predicting method outperforms the state-of-the-art methods by 5 %.

Influence Maximization Based on Dynamic Personal Perception in Knowledge Graph

“…iv) Amazon [51]: its KG has 260K nodes of 6 types and 1.4M edges of 6 types, including 20K items. Since there are no social relationships in Amazon, we supplement it with Pokec 29 (which has 1.6M users and 30.6M friendships) according to the user profiles [52]. To capture the complementary and substitutable relationships between items, the meta-graphs are generated according to [6], and the relevance of a certain relationship regarding a meta-graph is derived according to [14].…”

Incorporating Reverse Search for Friend Recommendation with Random Walk

“…Due to the constraints of huge social network scale coupled with the sparsity of relationships between users, efficient and accurate friend recommendation on social networks presents significant challenges [23]. Aiming at the above focuses, some studies [14,22,25,28] found that it can produce effective recommendation results by transforming social networks into web graphs and then applying random walk strategy.…”