On Application of Bayesian Parametric and Non-parametric Methods for User Cohorting in Product Search

Shashank Gupta


Abstract
In this paper, we study the applicability of Bayesian Parametric and Non-parametric methods for user clustering in an E-commerce search setting. To the best of our knowledge, this is the first work that presents a comparative study of various Bayesian clustering methods in the context of product search. Specifically, we cluster users based on their topical patterns from their respective product search queries. To evaluate the quality of the clusters formed, we perform a collaborative query recommendation task. Our findings indicate that simple parametric model like Latent Dirichlet Allocation (LDA) outperforms more sophisticated non-parametric methods like Distance Dependent Chinese Restaurant Process and Dirichlet Process-based clustering in both tasks.
Anthology ID:
2020.ecnlp-1.13
Volume:
Proceedings of the 3rd Workshop on e-Commerce and NLP
Month:
July
Year:
2020
Address:
Seattle, WA, USA
Editors:
Shervin Malmasi, Surya Kallumadi, Nicola Ueffing, Oleg Rokhlenko, Eugene Agichtein, Ido Guy
Venue:
ECNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
86–89
Language:
URL:
https://aclanthology.org/2020.ecnlp-1.13
DOI:
10.18653/v1/2020.ecnlp-1.13
Bibkey:
Cite (ACL):
Shashank Gupta. 2020. On Application of Bayesian Parametric and Non-parametric Methods for User Cohorting in Product Search. In Proceedings of the 3rd Workshop on e-Commerce and NLP, pages 86–89, Seattle, WA, USA. Association for Computational Linguistics.
Cite (Informal):
On Application of Bayesian Parametric and Non-parametric Methods for User Cohorting in Product Search (Gupta, ECNLP 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl-24-ws-corrections/2020.ecnlp-1.13.pdf
Video:
 http://slideslive.com/38931245