Rewriting null e-commerce queries to recommend products

In e-commerce applications product descriptions are often concise. E-Commerce search engines often have to deal with queries that cannot be easily matched to product inventory resulting in zero recall or null query situations. Null queries arise from differences in buyer and seller vocabulary or from the transient nature of products. In this paper, we describe a system that rewrites null e-commerce queries to find matching products as close to the original query as possible. The system uses query relaxation to rewrite null queries in order to match products. Using eBay as an example of a dynamic marketplace, we show how using temporal feedback that respects product category structure using the repository of expired products, we improve the quality of recommended results. The system is scalable and can be run in a high volume setting. We show through our experiments that high quality product recommendations for more than 25% of null queries are achievable.

[1]  Le Zhao,et al.  Term necessity prediction , 2010, CIKM.

[2]  W. Bruce Croft,et al.  Improving verbose queries using subset distribution , 2010, CIKM.

[3]  Nish Parikh,et al.  Buzz-based recommender system , 2009, WWW '09.

[4]  Sergei Vassilvitskii,et al.  Relaxation in text search using taxonomies , 2008, Proc. VLDB Endow..

[5]  Sreenivas Gollapudi,et al.  Efficient query rewrite for structured web queries , 2011, CIKM '11.

[6]  Vasudeva Varma,et al.  Tossing coins to trim long queries , 2011, SIGIR '11.

[7]  Maria Soledad Pera.  Improving Library Searches Using Word-Correlation Factors and Folksonomies , 2008 .

[8]  Mostafa Keikha,et al.  TEMPER: A Temporal Relevance Feedback Method , 2011, ECIR.

[9]  Vitor R. Carvalho,et al.  Reducing long queries using query quality predictors , 2009, SIGIR.

[10]  W. Bruce Croft,et al.  Analysis of long queries in a large scale search log , 2009, WSCD '09.

[11]  J. J. Rocchio,et al.  Relevance feedback in information retrieval , 1971 .

[12]  W. Bruce Croft,et al.  Modeling subset distributions for verbose queries , 2011, SIGIR.

[13]  Andrei Z. Broder,et al.  Robust classification of rare queries using web knowledge , 2007, SIGIR.

[14]  W. Bruce Croft,et al.  Discovering key concepts in verbose queries , 2008, SIGIR '08.

[15]  Benjamin Rey,et al.  Generating query substitutions , 2006, WWW '06.

[16]  Nish Parikh,et al.  Inferring semantic query relations from collective user behavior , 2008, CIKM '08.

[17]  Nish Parikh,et al.  User behavior in zero-recall ecommerce queries , 2011, SIGIR '11.

[18]  Rosie Jones,et al.  Query word deletion prediction , 2003, SIGIR.

[19]  Christopher D. Manning,et al.  Enriching the Knowledge Sources Used in a Maximum Entropy Part-of-Speech Tagger , 2000, EMNLP.

[20]  Ioannis Antonellis,et al.  Simrank++: query rewriting through link analysis of the clickgraph (poster) , 2008, WWW.

[21]  John F. Canny,et al.  Recommending ephemeral items at web scale , 2011, SIGIR.

[22]  Neel Sundaresan.  Recommender systems at the long tail , 2011, RecSys '11.

[23]  Donna K. Harman,et al.  Relevance feedback revisited , 1992, SIGIR '92.

[24]  Miles Efron,et al.  Estimation methods for ranking recent information , 2011, SIGIR.

[25]  Nish Parikh,et al.  Query suggestion for E-commerce sites , 2011, WSDM '11.

[26]  Ravi Kumar,et al.  Optimizing query rewrites for keyword-based advertising , 2008, EC '08.