Learning item Temporal dynamics for predicting buying sessions

Veronika Bogina, Tsvi Kuflik, Osnat Mokryn

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


Identifying whether an e-commerce session will end up in a buy is an ongoing research topic. A session predicted as a non-buying one may trigger recommender systems, thus increasing the probability of a buy. Alternatively, a session predicted as a buying session may enable recommender systems to predict additional items. In this work, we suggest a prediction model leveraging the temporal characteristics of both the session and the items clicked in that session. Our method introduces a buying probability per session as a function of the clicked-items recent purchase history, and the session temporal characteristics. Empirical results on imbalanced e-commerce dataset with more than nine million sessions demonstrate that we achieve high Precision, Recall and ROC in predicting whether a session ends up with a purchase. In a wider perspective, our findings shed light on the importance of considering items temporal dynamics in e-commerce sites recommendations.

Original languageEnglish
Title of host publicationProceedings of the 21st International Conference on Intelligent User Interfaces
PublisherAssociation for Computing Machinery
Number of pages5
ISBN (Print)9781450341370
StatePublished - 7 Mar 2016
Event21st International Conference on Intelligent User Interfaces, IUI 2016 - Sonoma, United States
Duration: 7 Mar 201610 Mar 2016

Publication series

NameInternational Conference on Intelligent User Interfaces, Proceedings IUI


Conference21st International Conference on Intelligent User Interfaces, IUI 2016
Country/TerritoryUnited States

Bibliographical note

Publisher Copyright:
© Copyright 2016 ACM.


  • Electronic commerce
  • Imbalanced Data Set
  • Machine Learning
  • Recommender Systems
  • Temporal Dynamics

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction


Dive into the research topics of 'Learning item Temporal dynamics for predicting buying sessions'. Together they form a unique fingerprint.

Cite this