E-commerce Recommendation with Personalized Promotion

Most existing e-commerce recommender systems aim to recommend the right products to a consumer, assuming the properties of each product are fixed. However, some properties, including price discount, can be personalized to respond to each consumer's preference. This paper studies how to automatically set the price discount when recommending a product, in light of the fact that the price will often alter a consumer's purchase decision. The key to optimizing the discount is to predict consumer's willingness-to-pay (WTP), namely, the highest price a consumer is willing to pay for a product. Purchase data used by traditional e-commerce recommender systems provide points below or above the decision boundary. In this paper we collected training data to better predict the decision boundary. We implement a new e-commerce mechanism adapted from laboratory lottery and auction experiments that elicit a rational customer's exact WTP for a small subset of products, and use a machine learning algorithm to predict the customer's WTP for other products. The mechanism is implemented on our own e-commerce website that leverages Amazon's data and subjects recruited via Mechanical Turk. The experimental results suggest that this approach can help predict WTP, and boost consumer satisfaction as well as seller profit.

[1]  Junyu Niu,et al.  FDU at TREC 2002: Filtering, Q&A, Web and Video Tasks , 2002, TREC.

[2]  Jordan J. Louviere,et al.  Design and Analysis of Simulated Consumer Choice or Allocation Experiments: An Approach Based on Aggregate Data , 1983 .

[3]  C. Plott,et al.  Misconceptions and Game Form Recognition of the BDM Method: Challenges to Theories of Revealed Preference and Framing , 2014 .

[4]  Min Ding.  An Incentive-Aligned Mechanism for Conjoint Analysis , 2007 .

[5]  William Vickrey,et al.  Counterspeculation, Auctions, And Competitive Sealed Tenders , 1961 .

[6]  Michael Hahsler,et al.  A REVIEW OF METHODS FOR MEASURING WILLINGNESS-TO-PAY , 2017 .

[7]  Jia Chen,et al.  Does product recommendation meet its waterloo in unexplored categories?: no, price comes to help , 2014, SIGIR.

[8]  Jack Abrams.  A New Method for Testing Pricing Decisions , 1964 .

[9]  Greg M. Allenby,et al.  On the Heterogeneity of Demand , 1998 .

[10]  Yew Jin Lim.  Variational Bayesian Approach to Movie Rating Prediction , 2007 .

[11]  Rohini K. Srihari,et al.  UB at TREC 11: Batch and Adaptive Filtering , 2002, TREC.

[12]  Yi Zhang.  Using bayesian priors to combine classifiers for adaptive filtering , 2004, SIGIR '04.

[13]  Sunil Gupta.  Impact of Sales Promotions on when, what, and how Much to Buy , 1988 .

[14]  Jörg Becker,et al.  Enabling individualized recommendations and dynamic pricing of value-added services through willingness-to-pay data , 2010, Electron. Mark..

[15]  Thomas Hofmann,et al.  A joint framework for collaborative and content filtering , 2004, SIGIR '04.

[16]  Roy G. Stout.  Developing Data to Estimate Price-quantity Relationships , 1969 .

[17]  Douglas B. Terry,et al.  Using collaborative filtering to weave an information tapestry , 1992, CACM.

[18]  Mohamed Abo-Rizka,et al.  A Conceptual Model of Personalized Pricing Recommender System Based on Customer Online Behavior , 2012 .

[19]  Stephen E. Robertson,et al.  The TREC-8 Filtering Track Final Report , 1999, TREC.

[20]  Clive W. J. Granger,et al.  Real and Hypothetical Shop Situations in Market Research , 1970 .

[21]  Thomas Hofmann,et al.  Latent Class Models for Collaborative Filtering , 1999, IJCAI.

[22]  Yiming Yang,et al.  Robustness of adaptive filtering methods in a cross-benchmark evaluation , 2005, SIGIR '05.

[23]  Greg M. Allenby,et al.  A Hierarchical Bayes Model of Primary and Secondary Demand , 1998 .

[24]  Christine D. Piatko,et al.  JHU/APL at TREC 2002: Experiments in Filtering and Arabic Retrieval , 2002, TREC.

[25]  Joel Huber,et al.  Improving Parameter Estimates and Model Prediction by Aggregate Customization in Choice Experiments , 2001 .

[26]  Min Ding,et al.  A simple mechanism to incentive-align conjoint experiments , 2010 .

[27]  M. Degroot,et al.  Measuring utility by a single-response sequential method. , 1964, Behavioral science.

[28]  Greg M. Allenby,et al.  Incorporating Prior Knowledge into the Analysis of Conjoint Studies , 1995 .

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

[30]  Shotaro Akaho,et al.  Personalized pricing recommender system: multi-stage epsilon-greedy approach , 2011, HetRec '11.

[31]  Klaus Miller,et al.  How Should Consumers’ Willingness to Pay be Measured? An Empirical Comparison of State-of-the-Art Approaches , 2011 .

[32]  Jian Wang,et al.  Utilizing marginal net utility for recommendation in e-commerce , 2011, SIGIR.

[33]  John F. Canny,et al.  Collaborative filtering with privacy via factor analysis , 2002, SIGIR '02.

[34]  Yehuda Koren,et al.  Matrix Factorization Techniques for Recommender Systems , 2009, Computer.

[35]  Arkadiusz Paterek,et al.  Improving regularized singular value decomposition for collaborative filtering , 2007 .