Entire Space Multi-Task Modeling via Post-Click Behavior Decomposition for Conversion Rate Prediction

Hong Wen*
Hong Wen*
Yuan Wang
Yuan Wang
Wentian Bao
Wentian Bao
Quan Lin
Quan Lin
Keping Yang
Keping Yang

SIGIR '20: The 43rd International ACM SIGIR conference on research and development in Information Retrieval Virtual Event China July, 2020, pp. 2377-2386, 2020.

Cited by: 0|Bibtex|Views52|DOI:https://doi.org/10.1145/3397271.3401443
EI
Other Links: dl.acm.org|dblp.uni-trier.de|academic.microsoft.com

Abstract:

Recommender system, as an essential part of modern e-commerce, consists of two fundamental modules, namely Click-Through Rate (CTR) and Conversion Rate (CVR) prediction. While CVR has a direct impact on the purchasing volume, its prediction is well-known challenging due to the Sample Selection Bias (SSB) and Data Sparsity (DS) issues. Alt...More

Code:

Data:

Your rating :
0

 

Tags
Comments