Malmö University Publications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Bandit Algorithms for e-Commerce Recommender Systems Extended Abstract
Apptus Technol, Trollebergsvagen 5, SE-22229 Lund, Sweden.
Apptus Technol, Trollebergsvagen 5, SE-22229 Lund, Sweden.
Malmö högskola, Faculty of Technology and Society (TS).ORCID iD: 0000-0002-1342-8618
Malmö högskola, Faculty of Technology and Society (TS).ORCID iD: 0000-0002-9767-5324
2017 (English)In: Proceedings of the Eleventh ACM Conference On Recommender Systems (Recsys'17), ACM Digital Library, 2017, p. 349-349Conference paper, Published paper (Refereed)
Abstract [en]

We study bandit algorithms for e-commerce recommender systems. The question we pose is whether it is necessary to consider reinforcement learning effects in recommender systems. A key reason to introduce a recommender system for a product page on an e-commerce site is to increase the order value by improving the chance of making an upsale. If the recommender system merely predicts the next purchase, there might be no positive effect at all on the order value, since the recommender system predicts sales that would have happened independent of the recommender system. What we really are looking for are the false negatives, i.e., purchases that happen as a consequence of the recommender system. These purchases entail the entire uplift and should be present as reinforcement learning effects. This effect cannot be displayed in a simulation of the site, since there are no reinforcement learning effects present in a simulation. The attribution model must capture the uplift to guarantee an increased order value. However, such an attribution model is not practical, due to data sparsity. Given this starting point, we study some standard attribution models for e-commerce recommender systems, and describe how these fare when applied in a reinforcement learning algorithm, both in a simulation and on live sites.

Place, publisher, year, edition, pages
ACM Digital Library, 2017. p. 349-349
Keywords [en]
Recommender systems, e-commerce, multi-arm bandits, Thompson sampling, ensemble learning
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:mau:diva-12335DOI: 10.1145/3109859.3109930ISI: 000426967000061Local ID: 27325OAI: oai:DiVA.org:mau-12335DiVA, id: diva2:1409381
Conference
11th ACM Conference on Recommender Systems, Como, Italy (August 27 - 31, 2017)
Available from: 2020-02-29 Created: 2020-02-29 Last updated: 2024-06-17Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full texthttps://recsys.acm.org/recsys17/

Authority records

Nilsson, Bengt J.Paraschakis, Dimitris

Search in DiVA

By author/editor
Nilsson, Bengt J.Paraschakis, Dimitris
By organisation
Faculty of Technology and Society (TS)
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 112 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf