Title:
SYSTEM AND METHOD FOR HANDLING POPULARITY BIAS IN ITEM RECOMMENDATIONS
Document Type and Number:
WIPO Patent Application WO/2021/038592
Kind Code:
A3
Abstract:
This disclosure relates generally to method and system for handling popularity bias in item recommendations. In an embodiment, the method includes initializing an item embedding look-up matrix corresponding to items in a sequence of item-clicks with respect to a training data. L2 norm is applied to the item embedding look-up matrix to learn a normalized item embeddings. Using a neural network, a session embeddings corresponding to the sequences of item-clicks is modeled and L2 norm is applied to the session embeddings to obtain a normalized session embeddings. Relevance scores corresponding to each of the plurality of items are obtained based on similarity between the normalized item embeddings and the normalized session embeddings. A multi-dimensional probability vector corresponding to the relevance scores for the items to be clicked in the sequence is obtained. A list of the items ordered based on the multi-dimensional probability vector is provided as recommendation.
Inventors:
MALHOTRA PANKAJ (IN)
GUPTA PRIYANKA (IN)
GARG DIKSHA (IN)
VIG LOVEKESH (IN)
SHROFF GAUTAM (IN)
GUPTA PRIYANKA (IN)
GARG DIKSHA (IN)
VIG LOVEKESH (IN)
SHROFF GAUTAM (IN)
Application Number:
PCT/IN2020/050744
Publication Date:
April 01, 2021
Filing Date:
August 25, 2020
Export Citation:
Assignee:
TATA CONSULTANCY SERVICES LTD (IN)
International Classes:
G06Q30/06; G06F16/9535; G06K9/62; G06N3/04; G06N3/08; G06N20/00
Domestic Patent References:
| WO2019017990A1 | 2019-01-24 | |||
| WO2018148493A1 | 2018-08-16 |
Foreign References:
| US20190251435A1 | 2019-08-15 |
Other References:
HIDASI ET AL.: "Parallel Recurrent Neural Network Architectures for Feature-rich Session-based Recommendations", PROCEEDINGS OF THE 10TH ACM CONFERENCE ON RECOMMENDER SYSTEMS, 19 September 2016 (2016-09-19), pages 241 - 248, XP058278071, Retrieved from the Internet [retrieved on 20210121]
HU GUANGNENG, ZHANG YU: "Personalized Neural Embeddings for Collaborative Filtering with Unstructured Text", ARXIV.ORG, 20190319 CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853,, 31 December 2018 (2018-12-31), pages 1 - 8, XP081155182, Retrieved from the Internet [retrieved on 20210121]
GUPTA PRIYANKA, GARG DIKSHA, MALHOTRA PANKAJ, VIG LOVEKESH, SHROFF GAUTAM: "NISER: Normalized Item and Session Representations to Handle Popularity Bias", ARXIV.ORG, 20190910 CORNELL UNIVERSITY LIBRARY,, 12 December 2019 (2019-12-12), 201 Olin Library Cornell University Ithaca, NY 14853, pages 1 - 6, XP081550065, Retrieved from the Internet [retrieved on 20210121]
HUANG JIMMY, CHANG YI, CHENG XUEQI, KAMPS JAAP, MURDOCK VANESSA, WEN JI-RONG, LIU YIQUN, LIU SIWEI, OUNIS IADH, MACDONALD CRAIG, M: "A Heterogeneous Graph Neural Model for*Cold-start Recommendation", 30 July 2020 (2020-07-30), pages 2029 - 2032, XP058465287, Retrieved from the Internet [retrieved on 20210121]
HU GUANGNENG, ZHANG YU: "Personalized Neural Embeddings for Collaborative Filtering with Unstructured Text", ARXIV.ORG, 20190319 CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853,, 31 December 2018 (2018-12-31), pages 1 - 8, XP081155182, Retrieved from the Internet
GUPTA PRIYANKA, GARG DIKSHA, MALHOTRA PANKAJ, VIG LOVEKESH, SHROFF GAUTAM: "NISER: Normalized Item and Session Representations to Handle Popularity Bias", ARXIV.ORG, 20190910 CORNELL UNIVERSITY LIBRARY,, 12 December 2019 (2019-12-12), 201 Olin Library Cornell University Ithaca, NY 14853, pages 1 - 6, XP081550065, Retrieved from the Internet
HUANG JIMMY, CHANG YI, CHENG XUEQI, KAMPS JAAP, MURDOCK VANESSA, WEN JI-RONG, LIU YIQUN, LIU SIWEI, OUNIS IADH, MACDONALD CRAIG, M: "A Heterogeneous Graph Neural Model for*Cold-start Recommendation", 30 July 2020 (2020-07-30), pages 2029 - 2032, XP058465287, Retrieved from the Internet
Attorney, Agent or Firm:
GEHLOT, Aditi et al. (IN)
Download PDF: