Perceive Your Users in Depth: Learning Universal User Representations from Multiple E-commerce Tasks

Tasks such as search and recommendation have become increas- ingly important for E-commerce to deal with the information over- load problem. To meet the diverse needs of di erent users, person- alization plays an important role. In many large portals such as Taobao and Amazon, there are a bunch of d...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ni, Yabo, Ou, Dan, Liu, Shichen, Li, Xiang, Ou, Wenwu, Zeng, Anxiang, Si, Luo
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Ni, Yabo
Ou, Dan
Liu, Shichen
Li, Xiang
Ou, Wenwu
Zeng, Anxiang
Si, Luo
description Tasks such as search and recommendation have become increas- ingly important for E-commerce to deal with the information over- load problem. To meet the diverse needs of di erent users, person- alization plays an important role. In many large portals such as Taobao and Amazon, there are a bunch of di erent types of search and recommendation tasks operating simultaneously for person- alization. However, most of current techniques address each task separately. This is suboptimal as no information about users shared across di erent tasks. In this work, we propose to learn universal user representations across multiple tasks for more e ective personalization. In partic- ular, user behavior sequences (e.g., click, bookmark or purchase of products) are modeled by LSTM and attention mechanism by integrating all the corresponding content, behavior and temporal information. User representations are shared and learned in an end-to-end setting across multiple tasks. Bene ting from better information utilization of multiple tasks, the user representations are more e ective to re ect their interests and are more general to be transferred to new tasks. We refer this work as Deep User Perception Network (DUPN) and conduct an extensive set of o ine and online experiments. Across all tested ve di erent tasks, our DUPN consistently achieves better results by giving more e ective user representations. Moreover, we deploy DUPN in large scale operational tasks in Taobao. Detailed implementations, e.g., incre- mental model updating, are also provided to address the practical issues for the real world applications.
doi_str_mv 10.48550/arxiv.1805.10727
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1805_10727</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1805_10727</sourcerecordid><originalsourceid>FETCH-LOGICAL-a677-7a2caf8767f425341f430d78e55234c890f8a6c67ea2b081227b61f8cc95fbb53</originalsourceid><addsrcrecordid>eNotj7tOwzAUQL0woMIHMHF_IMF24thlQ6U8pCIQSgem6Ma9BovEiey0gr-HBqazHB3pMHYheF4apfgVxi9_yIXhKhdcS33Kdi8ULfkDwduwj7BNFBP4ALc0Th_XsCGMwYd32IZfJybsZgVeaYyUKEw4-SEkcHHo4WnfTX7sCNaZHfr-GIYa02c6YycOu0Tn_1yw-m5drx6yzfP94-pmk2GldaZRWnRGV9qVUhWlcGXBd9qQUrIorVlyZ7CylSaULTdCSt1Wwhlrl8q1rSoW7PIvO282Y_Q9xu_muNvMu8UPOExQpw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Perceive Your Users in Depth: Learning Universal User Representations from Multiple E-commerce Tasks</title><source>arXiv.org</source><creator>Ni, Yabo ; Ou, Dan ; Liu, Shichen ; Li, Xiang ; Ou, Wenwu ; Zeng, Anxiang ; Si, Luo</creator><creatorcontrib>Ni, Yabo ; Ou, Dan ; Liu, Shichen ; Li, Xiang ; Ou, Wenwu ; Zeng, Anxiang ; Si, Luo</creatorcontrib><description>Tasks such as search and recommendation have become increas- ingly important for E-commerce to deal with the information over- load problem. To meet the diverse needs of di erent users, person- alization plays an important role. In many large portals such as Taobao and Amazon, there are a bunch of di erent types of search and recommendation tasks operating simultaneously for person- alization. However, most of current techniques address each task separately. This is suboptimal as no information about users shared across di erent tasks. In this work, we propose to learn universal user representations across multiple tasks for more e ective personalization. In partic- ular, user behavior sequences (e.g., click, bookmark or purchase of products) are modeled by LSTM and attention mechanism by integrating all the corresponding content, behavior and temporal information. User representations are shared and learned in an end-to-end setting across multiple tasks. Bene ting from better information utilization of multiple tasks, the user representations are more e ective to re ect their interests and are more general to be transferred to new tasks. We refer this work as Deep User Perception Network (DUPN) and conduct an extensive set of o ine and online experiments. Across all tested ve di erent tasks, our DUPN consistently achieves better results by giving more e ective user representations. Moreover, we deploy DUPN in large scale operational tasks in Taobao. Detailed implementations, e.g., incre- mental model updating, are also provided to address the practical issues for the real world applications.</description><identifier>DOI: 10.48550/arxiv.1805.10727</identifier><language>eng</language><subject>Computer Science - Learning ; Statistics - Machine Learning</subject><creationdate>2018-05</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1805.10727$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1805.10727$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Ni, Yabo</creatorcontrib><creatorcontrib>Ou, Dan</creatorcontrib><creatorcontrib>Liu, Shichen</creatorcontrib><creatorcontrib>Li, Xiang</creatorcontrib><creatorcontrib>Ou, Wenwu</creatorcontrib><creatorcontrib>Zeng, Anxiang</creatorcontrib><creatorcontrib>Si, Luo</creatorcontrib><title>Perceive Your Users in Depth: Learning Universal User Representations from Multiple E-commerce Tasks</title><description>Tasks such as search and recommendation have become increas- ingly important for E-commerce to deal with the information over- load problem. To meet the diverse needs of di erent users, person- alization plays an important role. In many large portals such as Taobao and Amazon, there are a bunch of di erent types of search and recommendation tasks operating simultaneously for person- alization. However, most of current techniques address each task separately. This is suboptimal as no information about users shared across di erent tasks. In this work, we propose to learn universal user representations across multiple tasks for more e ective personalization. In partic- ular, user behavior sequences (e.g., click, bookmark or purchase of products) are modeled by LSTM and attention mechanism by integrating all the corresponding content, behavior and temporal information. User representations are shared and learned in an end-to-end setting across multiple tasks. Bene ting from better information utilization of multiple tasks, the user representations are more e ective to re ect their interests and are more general to be transferred to new tasks. We refer this work as Deep User Perception Network (DUPN) and conduct an extensive set of o ine and online experiments. Across all tested ve di erent tasks, our DUPN consistently achieves better results by giving more e ective user representations. Moreover, we deploy DUPN in large scale operational tasks in Taobao. Detailed implementations, e.g., incre- mental model updating, are also provided to address the practical issues for the real world applications.</description><subject>Computer Science - Learning</subject><subject>Statistics - Machine Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj7tOwzAUQL0woMIHMHF_IMF24thlQ6U8pCIQSgem6Ma9BovEiey0gr-HBqazHB3pMHYheF4apfgVxi9_yIXhKhdcS33Kdi8ULfkDwduwj7BNFBP4ALc0Th_XsCGMwYd32IZfJybsZgVeaYyUKEw4-SEkcHHo4WnfTX7sCNaZHfr-GIYa02c6YycOu0Tn_1yw-m5drx6yzfP94-pmk2GldaZRWnRGV9qVUhWlcGXBd9qQUrIorVlyZ7CylSaULTdCSt1Wwhlrl8q1rSoW7PIvO282Y_Q9xu_muNvMu8UPOExQpw</recordid><startdate>20180527</startdate><enddate>20180527</enddate><creator>Ni, Yabo</creator><creator>Ou, Dan</creator><creator>Liu, Shichen</creator><creator>Li, Xiang</creator><creator>Ou, Wenwu</creator><creator>Zeng, Anxiang</creator><creator>Si, Luo</creator><scope>AKY</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20180527</creationdate><title>Perceive Your Users in Depth: Learning Universal User Representations from Multiple E-commerce Tasks</title><author>Ni, Yabo ; Ou, Dan ; Liu, Shichen ; Li, Xiang ; Ou, Wenwu ; Zeng, Anxiang ; Si, Luo</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a677-7a2caf8767f425341f430d78e55234c890f8a6c67ea2b081227b61f8cc95fbb53</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Computer Science - Learning</topic><topic>Statistics - Machine Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Ni, Yabo</creatorcontrib><creatorcontrib>Ou, Dan</creatorcontrib><creatorcontrib>Liu, Shichen</creatorcontrib><creatorcontrib>Li, Xiang</creatorcontrib><creatorcontrib>Ou, Wenwu</creatorcontrib><creatorcontrib>Zeng, Anxiang</creatorcontrib><creatorcontrib>Si, Luo</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Ni, Yabo</au><au>Ou, Dan</au><au>Liu, Shichen</au><au>Li, Xiang</au><au>Ou, Wenwu</au><au>Zeng, Anxiang</au><au>Si, Luo</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Perceive Your Users in Depth: Learning Universal User Representations from Multiple E-commerce Tasks</atitle><date>2018-05-27</date><risdate>2018</risdate><abstract>Tasks such as search and recommendation have become increas- ingly important for E-commerce to deal with the information over- load problem. To meet the diverse needs of di erent users, person- alization plays an important role. In many large portals such as Taobao and Amazon, there are a bunch of di erent types of search and recommendation tasks operating simultaneously for person- alization. However, most of current techniques address each task separately. This is suboptimal as no information about users shared across di erent tasks. In this work, we propose to learn universal user representations across multiple tasks for more e ective personalization. In partic- ular, user behavior sequences (e.g., click, bookmark or purchase of products) are modeled by LSTM and attention mechanism by integrating all the corresponding content, behavior and temporal information. User representations are shared and learned in an end-to-end setting across multiple tasks. Bene ting from better information utilization of multiple tasks, the user representations are more e ective to re ect their interests and are more general to be transferred to new tasks. We refer this work as Deep User Perception Network (DUPN) and conduct an extensive set of o ine and online experiments. Across all tested ve di erent tasks, our DUPN consistently achieves better results by giving more e ective user representations. Moreover, we deploy DUPN in large scale operational tasks in Taobao. Detailed implementations, e.g., incre- mental model updating, are also provided to address the practical issues for the real world applications.</abstract><doi>10.48550/arxiv.1805.10727</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.1805.10727
ispartof
issn
language eng
recordid cdi_arxiv_primary_1805_10727
source arXiv.org
subjects Computer Science - Learning
Statistics - Machine Learning
title Perceive Your Users in Depth: Learning Universal User Representations from Multiple E-commerce Tasks
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T23%3A39%3A07IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Perceive%20Your%20Users%20in%20Depth:%20Learning%20Universal%20User%20Representations%20from%20Multiple%20E-commerce%20Tasks&rft.au=Ni,%20Yabo&rft.date=2018-05-27&rft_id=info:doi/10.48550/arxiv.1805.10727&rft_dat=%3Carxiv_GOX%3E1805_10727%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true