Back-buy prediction based on TriFG

Reciprocal Relationship in twitter can be predicted by TriFG model. Based on this model, we study the extent to which the formation of a two-way relationship can be predicted in a dynamic e-commerce web site which is composed of products and customers, especially the back-buy behavior. Back-buy behavior represents a more stable interest direction of customers. Understanding the formation of back-buy behavior can provide us insights into the potential e-commerce trends and lead to more efficient advertisement. In this paper, we propose a learning framework to formulate the problem of back-buy prediction into a graphical model---Back-buy model (BBModel). Employing such e-shopping sites as Amazon as a source for our experimental data, BBModel can predict the probability of the customers back and buy the products. Finally, the experiments show that the BBModel is feasible and effective for prediction. The two-way relationship prediction can fit to the e-commerce web site.

[1]  J. M. Hammersley,et al.  Markov fields on finite graphs and lattices , 1971 .

[2]  Jie Tang,et al.  Who will follow you back?: reciprocal relationship prediction , 2011, CIKM '11.

[3]  Jie Tang,et al.  Inferring social ties across heterogenous networks , 2012, WSDM '12.

[4]  Michael I. Jordan,et al.  Loopy Belief Propagation for Approximate Inference: An Empirical Study , 1999, UAI.

[5]  Jennifer Neville,et al.  Randomization tests for distinguishing social influence and homophily effects , 2010, WWW '10.

[6]  M. Newman.  Clustering and preferential attachment in growing networks. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[7]  Roger Jianxin Jiao,et al.  An associative classification-based recommendation system for personalization in B2C e-commerce applications , 2007, Expert Syst. Appl..

[8]  Yue Xu,et al.  Integrating Collaborative Filtering and Search-Based Techniques for Personalized Online Product Recommendation , 2011, 2011 IEEE 11th International Conference on Data Mining Workshops.

[9]  Bo Zhao,et al.  PET: a statistical model for popular events tracking in social communities , 2010, KDD.

[10]  Srinivasan Parthasarathy,et al.  Local Probabilistic Models for Link Prediction , 2007, Seventh IEEE International Conference on Data Mining (ICDM 2007).

[11]  Jure Leskovec,et al.  The dynamics of viral marketing , 2005, EC '06.

[12]  John Riedl,et al.  GroupLens: an open architecture for collaborative filtering of netnews , 1994, CSCW '94.

[13]  Aaron Tay.  CSCW '94 , 1995, SGCH.

[14]  Nitesh V. Chawla,et al.  New perspectives and methods in link prediction , 2010, KDD.

[15]  D. Horton,et al.  Mass communication and para-social interaction; observations on intimacy at a distance. , 1956, Psychiatry.

[16]  Peter H. Reingen,et al.  Social Ties and Word-of-Mouth Referral Behavior , 1987 .

[17]  Elaine Rich,et al.  User Modeling via Stereotypes , 1998, Cogn. Sci..

[18]  Fabrice Guillet,et al.  CAPRE: A New Methodology for Product Recommendation Based on Customer Actionability and Profitability , 2011, 2011 IEEE 11th International Conference on Data Mining Workshops.

[19]  Jure Leskovec,et al.  Supervised random walks: predicting and recommending links in social networks , 2010, WSDM '11.

[20]  David Liben-Nowell,et al.  The link-prediction problem for social networks , 2007 .

[21]  Jure Leskovec,et al.  Predicting positive and negative links in online social networks , 2010, WWW '10.

[22]  Leo Katz,et al.  A new status index derived from sociometric analysis , 1953 .