PROJECT TITLE :

A Unified View of Social and Temporal Modeling for B2B Marketing Campaign Recommendation - 2018

ABSTRACT:

Business to Business (B2B) promoting aims at meeting the wants of different businesses rather than individual consumers, and so entails management of a lot of complex business desires than consumer selling. The shopping for processes of the business customers involve series of different selling campaigns providing multifaceted information regarding the products or services. Whereas most existing studies specialize in individual consumers, very little has been done to guide business customers because of the dynamic and complex nature of these business shopping for processes. To this end, during this Project, we have a tendency to focus on providing a unified view of social and temporal modeling for B2B promoting campaign recommendation. Along this line, we tend to initial exploit the temporal behavior patterns in the B2B shopping for processes and develop a marketing campaign recommender system. Specifically, we have a tendency to begin with constructing a temporal graph as the knowledge representation of the buying process of each business customer. Temporal graph can effectively extract and integrate the campaign order preferences of individual business customers. It is conjointly price noting that our system is backward compatible since the collaborating frequency employed in typical static recommender systems is of course embedded in our temporal graph. The campaign recommender is then engineered during a low-rank graph reconstruction framework primarily based on probabilistic graphical models. Our framework will determine the common graph patterns and predict missing edges within the temporal graphs. In addition, since business customers very often have completely different call makers from the identical company, we additionally incorporate social factors, like community relationships of the business customers, for more improving overall performances of the missing edge prediction and recommendation. Finally, we have a tendency to have performed in depth empirical studies on real-world B2B marketing data sets and therefore the results show that the proposed method will effectively improve the standard of the campaign recommendations for difficult B2B marketing tasks.