Transient Group Recommendation for Shared Environment using Check-in and Tag Data

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Group Recommendation Systems (GRSs) are crucial in facilitating decision-making processes for shared playlists. However, recommending appropriate items is challenging when it comes to dynamic and transient groups such as restaurant customers. Thus, we proposed a hybrid GRS designed to address these difficulties. By combining collaborative filtering and content-based recommendations enriched with tag information, the proposed system used historical and current check-in data to predict future group composition and tailor recommendations accordingly. The system generated top-N music playlists for every period of the week and provided diverse and novel recommendations prepared before customers' arrival. We enhanced recommendation performance by extending the traditional user-item matrix with tags and combining memory-based and model-based computation. The proposed method was tested with two real-world datasets. The result showed the improvement of the performance over popularity-based item selection, offering a promising approach for transient group recommendation in a shared environment.

Original languageEnglish
Title of host publicationProceedings of the 2023 IEEE 6th International Conference on Knowledge Innovation and Invention, ICKII 2023
EditorsTeen-Hang Meen
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages661-666
Number of pages6
ISBN (Electronic)9798350323535
DOIs
Publication statusPublished - 2023
Event6th IEEE International Conference on Knowledge Innovation and Invention, ICKII 2023 - Sapporo, Japan
Duration: 2023 Aug 112023 Aug 13

Publication series

NameProceedings of the 2023 IEEE 6th International Conference on Knowledge Innovation and Invention, ICKII 2023

Conference

Conference6th IEEE International Conference on Knowledge Innovation and Invention, ICKII 2023
Country/TerritoryJapan
CitySapporo
Period23-08-1123-08-13

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Software
  • Decision Sciences (miscellaneous)
  • Information Systems and Management
  • Control and Systems Engineering
  • Control and Optimization
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Transient Group Recommendation for Shared Environment using Check-in and Tag Data'. Together they form a unique fingerprint.

Cite this