EEMCS

Home > Publications
Home University of Twente
Education
Research
Prospective Students
Jobs
Publications
Intranet (internal)
 
 Nederlands
 Contact
 Search
 Organisation

EEMCS EPrints Service


27194 Beyond Movie Recommendations: Solving the Continuous Cold Start Problem in E-commerce Recommendations
Home Policy Brochure Browse Search User Area Contact Help

Kiseleva, J. and Tuzhilin, A. and Kamps, J. and Bernardi, L. and Davis, C. and Kovacek, I. and Einarsen, M. S. and Hiemstra, D. (2016) Beyond Movie Recommendations: Solving the Continuous Cold Start Problem in E-commerce Recommendations. Technical Report 1607.07904, Cornell university, Ithaca, NY, USA. ISSN 2331-8422

Full text available as:

PDF

1016 Kb
Open Access



Official URL: http://dx.doi.org/10.13140/RG.2.1.2488.7288

Abstract

Many e-commerce websites use recommender systems or personalized rankers to personalize search results based on their previous interactions. However, a large fraction of users has no prior inter-actions, making it impossible to use collaborative filtering or rely on user history for personalization. Even the most active users mayvisit only a few times a year and may have volatile needs or different personas, making their personal history a sparse and noisy signal at best. This paper investigates how, when we cannot rely on the user history, the large scale availability of other user interactions still allows us to build meaningful profiles from the contextual data and whether such contextual profiles are useful to customize the ranking, exemplified by data from a major online travel agentBooking.com.Our main findings are threefold: First, we characterize the Continuous Cold Start Problem(CoCoS) from the viewpoint of typical e-commerce applications. Second, as explicit situational con-text is not available in typical real world applications, implicit cues from transaction logs used at scale can capture essential features of situational context. Third, contextual user profiles can be created offline, resulting in a set of smaller models compared to a single huge non-contextual model, making contextual ranking available with negligible CPU and memory footprint. Finally we conclude that, in an online A/B test on live users, our contextual ranker in-creased user engagement substantially over a non-contextual base-line, with click-through-rate (CTR) increased by 20%. This clearly demonstrates the value of contextual user profiles in a real world application.

Item Type:Internal Report (Technical Report)
Research Group:EWI-DB: Databases
Research Program:CTIT-General
Research Project:COMMIT/Infiniti: Information Retrieval for Information Services
ID Code:27194
Deposited On:20 April 2017
Refereed:No
International:Yes
More Information:statistics

Export this item as:

To correct this item please ask your editor

Repository Staff Only: edit this item