Context and customer behaviour in recommendation
Warwick Research Archive Portal (University of Warwick)Published 1 October 2009Open access
S. Lombardi, Sarabjot Singh Anand, Michele Gorgoglione
Citations20
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The effect of incorporating contextual variables, both observable and derived from past user behavior, on the accuracy of a content based recommender system is studied.
Abstract
The last few years have seen an increased interest in incorporating context within recommender systems. However, little empirical evidence has emerged to support the premise that context can actually improve recommendation accuracy. Indeed little agreement exists as to what represents the context of a user or indeed how such context should be used within a recommendation strategy. In this paper we study the effect of incorporating contextual variables, both observable and derived from past user behavior, on the accuracy of a content based recommender system. The system was evaluated using data from an Italian online retailer. Results suggest a significant improvement in performance when using contextual variables.
Keywords
Computer ScienceBusiness, Management and Accounting
Elsevier eBooksData Mining: Practical Machine Learning Tools and Techniques
25,718 Citations2011Ian H. Witten, Eibe Frank
Modern Information Retrieval
11,544 Citations1999Ricardo Baeza‐Yates, Berthier Ribeiro‐Neto
IEEE Transactions on Knowledge and Data EngineeringToward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions
10,115 Citations2005Gediminas Adomavičius, Alexander Tuzhilin
This paper presents an overview of the field of recommender systems and describes the current generation of recommendation methods that are usually classified into the following three main categories: content-based, collaborative, and hybrid recommendation approaches.
The American Journal of PsychologyPlans and Situated Actions: The Problem of Human-Machine Communication
5,333 Citations1990Barry H. Kantowitz, Lucy Suchman
This paper presents a meta-modelling architecture for human-machine communication that automates the very labor-intensive and therefore time-heavy and therefore expensive and expensive process of designing and implementing communication systems.
Communications of the ACMFab
2,927 Citations1997Marko Balabanović, Yoav Shoham
It is explained how a hybrid system can incorporate the advantages of both methods while inheriting the disadvantages of neither, and how the particular design of the Fab architecture brings two additional benefits.
Journal of Consumer ResearchConstructive Consumer Choice Processes
2,768 Citations1998James R. Bettman, Mary Frances Luce +1 more
Communications of the ACMInformation filtering and information retrieval
1,288 Citations1992Nicholas J. Belkin, W. Bruce Croft
Models of information retrieval and filtering, and lessons for filtering from retrieval research are presented; users see only the data that is extracted.
ACM Transactions on Information SystemsIncorporating contextual information in recommender systems using a multidimensional approach
1,186 Citations2005Gediminas Adomavičius, Ramesh Sankaranarayanan +2 more
A multidimensional (MD) approach to recommender systems that can provide recommendations based on additional contextual information besides the typical information on users and items used in most of the currentRecommender systems is presented.
Recommendation as classification: using social and content-based information in recommendation
955 Citations1998Chumki Basu, Haym Hirsh +1 more
These sulfoxides and sulfones are useful as analgesics, non-addicting narcotic antagonists and anti-diarrheal agents and having agonist activity at opiate receptors are disclosed herein.
Syskill & webert: Identifying interesting web sites
595 Citations1996Michael J. Pazzani, Jack Muramatsu +1 more
The naive Bayesian classifier offers several advantages over other learning algorithms on this task and an initial portion of a web page is sufficient for making predictions on its interestingness substantially reducing the amount of network transmission required to make predictions.
Data Mining and Knowledge DiscoveryDiscovery and Evaluation of Aggregate Usage Profiles for Web Personalization
379 Citations2002Bamshad Mobasher, Honghua Dai +2 more
The results indicate that using the generated aggregate profiles, the technique can achieve effective personalization at early stages of users' visits to a site, based only on anonymous clickstream data and without the benefit of explicit input by these users or deeper knowledge about them.
IEEE Transactions on Knowledge and Data EngineeringUsing Context to Improve Predictive Modeling of Customers in Personalization Applications
199 Citations2008Cosimo Palmisano, Alexander Tuzhilin +1 more
It is shown that context does matter when modeling the behavior of individual customers and that it is possible to infer the context from the existing data with reasonable accuracy in certain cases and that significant performance improvements can be achieved if the context is "cleverly" modeled.
Lecture notes in computer scienceIntelligent Techniques for Web Personalization
160 Citations2005Bamshad Mobasher, Sarabjot Singh Anand +1 more
Lecture notes in computer scienceContextual Recommendation
82 Citations2007Sarabjot Singh Anand, Bamshad Mobasher
This paper proposes a fundamental shift in terms of how a user is modeled within a recommendation system, inspired by models of human memory developed in psychology, and defines a recommendation process that uses these two memories.