Header

UZH-Logo

Maintenance Infos

Getting the timing right: leveraging category inter-purchase times to improve recommender systems


Vuckovac, Denis; Wamsler, Julia; Ilic, Alexander; Natter, Martin (2016). Getting the timing right: leveraging category inter-purchase times to improve recommender systems. In: ACM Conference on Recommender Systems 2016 (RecSys 2016), Boston, 15 September 2016 - 19 September 2016. ACM, Association for Computing Machinery, 277-280.

Abstract

In the marketing domain, models of grocery buying behavior consider purchase incidence as a key dimension. However, in recommender systems, timing is often subsumed under contextual information and has received little attention yet. For this reason, we analyze the relation between the timing of a recommendation and its acceptance across different product categories. Our study is based on a real-world deployment of an in-store recommendation system in the brick-and-mortar grocery industry. We base our analysis on transaction data of more than 100,000 unique users and more than four million product recommendations. Our findings suggest that the success of a recommendation significantly depends on the inter-purchase time within the respective category. Different sensitivities across product categories further stress the importance of timing and its interplay with category characteristics within the context of recommender systems. The insights gained in this study enable retailers to improve scheduling recommendations and target promotions more efficiently.

Abstract

In the marketing domain, models of grocery buying behavior consider purchase incidence as a key dimension. However, in recommender systems, timing is often subsumed under contextual information and has received little attention yet. For this reason, we analyze the relation between the timing of a recommendation and its acceptance across different product categories. Our study is based on a real-world deployment of an in-store recommendation system in the brick-and-mortar grocery industry. We base our analysis on transaction data of more than 100,000 unique users and more than four million product recommendations. Our findings suggest that the success of a recommendation significantly depends on the inter-purchase time within the respective category. Different sensitivities across product categories further stress the importance of timing and its interplay with category characteristics within the context of recommender systems. The insights gained in this study enable retailers to improve scheduling recommendations and target promotions more efficiently.

Statistics

Citations

Dimensions.ai Metrics
2 citations in Web of Science®
2 citations in Scopus®
Google Scholar™

Altmetrics

Downloads

88 downloads since deposited on 28 Aug 2019
24 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Business Administration
Dewey Decimal Classification:330 Economics
Scopus Subject Areas:Physical Sciences > Control and Systems Engineering
Physical Sciences > Hardware and Architecture
Physical Sciences > Computer Networks and Communications
Language:English
Event End Date:19 September 2016
Deposited On:28 Aug 2019 13:51
Last Modified:10 Mar 2023 08:02
Publisher:ACM, Association for Computing Machinery
Series Name:RecSys '16 Proceedings of the 10th ACM Conference on Recommender Systems
Number:10
ISBN:978-1-4503-4035-9
OA Status:Green
Free access at:Publisher DOI. An embargo period may apply.
Publisher DOI:https://doi.org/10.1145/2959100.2959184
Other Identification Number:merlin-id:18064
  • Content: Published Version