Hybrid deep modelling with human knowledge in practical e-commerce search

In recent years, recommender systems have become increasingly important in the E-commerce marketplaces (e.g., Alibaba, Amazon). According to public information, recommender systems have contributed 30% gross merchandise value (GMV) for Amazon. Significant effort has been devoted into this researc...

Full description

Saved in:
Bibliographic Details
Main Author: Zeng, Anxiang
Other Authors: Miao Chun Yan
Format: Thesis-Doctor of Philosophy
Language:English
Published: Nanyang Technological University 2024
Subjects:
Online Access:https://hdl.handle.net/10356/173988
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-173988
record_format dspace
spelling sg-ntu-dr.10356-1739882024-04-09T03:58:58Z Hybrid deep modelling with human knowledge in practical e-commerce search Zeng, Anxiang Miao Chun Yan Yu Han School of Computer Science and Engineering han.yu@ntu.edu.sg, ASCYMiao@ntu.edu.sg Computer and Information Science E-commerce Deep learning In recent years, recommender systems have become increasingly important in the E-commerce marketplaces (e.g., Alibaba, Amazon). According to public information, recommender systems have contributed 30% gross merchandise value (GMV) for Amazon. Significant effort has been devoted into this research field by the industry and the academic community. Research works making key advances in recommendation systems can be divided into matrix factorization (MF), collaborative filtering (CF) and click-through rate (CTR) prediction. Currently, in industrial e-commerce recommendation systems, the main adopted approach is to use CF methods for performing recall tasks and deep learning-based CTR prediction methods for performing ranking tasks. However, significant challenges remain when these algorithms are to be deployed into practical e-commerce environments. In the system of search, most of the ctr modeling use big data, with a large number of user behavior data. The amount of data is a large number, which is very helpful to build the model. At the same time, these data also contains a lot of noise. This can lead to inaccurate modeling. In many cases, these behaviors are not consistent with business needs, we need to make manual guidance and intervention to the model. Doctor of Philosophy 2024-03-11T08:10:57Z 2024-03-11T08:10:57Z 2023 Thesis-Doctor of Philosophy Zeng, A. (2023). Hybrid deep modelling with human knowledge in practical e-commerce search. Doctoral thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/173988 https://hdl.handle.net/10356/173988 10.32657/10356/173988 en This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0). application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Computer and Information Science
E-commerce
Deep learning
spellingShingle Computer and Information Science
E-commerce
Deep learning
Zeng, Anxiang
Hybrid deep modelling with human knowledge in practical e-commerce search
description In recent years, recommender systems have become increasingly important in the E-commerce marketplaces (e.g., Alibaba, Amazon). According to public information, recommender systems have contributed 30% gross merchandise value (GMV) for Amazon. Significant effort has been devoted into this research field by the industry and the academic community. Research works making key advances in recommendation systems can be divided into matrix factorization (MF), collaborative filtering (CF) and click-through rate (CTR) prediction. Currently, in industrial e-commerce recommendation systems, the main adopted approach is to use CF methods for performing recall tasks and deep learning-based CTR prediction methods for performing ranking tasks. However, significant challenges remain when these algorithms are to be deployed into practical e-commerce environments. In the system of search, most of the ctr modeling use big data, with a large number of user behavior data. The amount of data is a large number, which is very helpful to build the model. At the same time, these data also contains a lot of noise. This can lead to inaccurate modeling. In many cases, these behaviors are not consistent with business needs, we need to make manual guidance and intervention to the model.
author2 Miao Chun Yan
author_facet Miao Chun Yan
Zeng, Anxiang
format Thesis-Doctor of Philosophy
author Zeng, Anxiang
author_sort Zeng, Anxiang
title Hybrid deep modelling with human knowledge in practical e-commerce search
title_short Hybrid deep modelling with human knowledge in practical e-commerce search
title_full Hybrid deep modelling with human knowledge in practical e-commerce search
title_fullStr Hybrid deep modelling with human knowledge in practical e-commerce search
title_full_unstemmed Hybrid deep modelling with human knowledge in practical e-commerce search
title_sort hybrid deep modelling with human knowledge in practical e-commerce search
publisher Nanyang Technological University
publishDate 2024
url https://hdl.handle.net/10356/173988
_version_ 1800916355250126848