Workshop Description

In 2016, retail e-commerce sales worldwide amounted close to 2 trillion US dollars and e-retail revenues are projected to grow to 3.4 trillion US dollars in 2019. However, the rapid transition from the brick-and-mortar shops of old economy is still heavily limited by technology – specifically, the limitations of online product searches, which, especially compared to a conversation with a real world sales associate, return far too many irrelevant and unspecific results to be of reliably convenient use. The key to unlocking the next wave of e-commerce disruption has arrived, this time with the advent of artificial intelligence (AI). We aim to bring the attention of researchers to real problems with AI applications in E-Commerce, ranging from search, recommendation, (re)targeting, information retrieval and natural language processing (NLP) that belong to the regular IT areas, to the business advisory ChatBot belonging to the hot arising areas, etc. In the recent past years, researchers have proposed various AI techniques in the above mentioned application areas.

Important Dates

Abstract Submission - June 03 Paper Submission - June 15 Author Notification - June 30 IJCAI Early registration deadline - June 30 Final Version - July 30 Please submit your final version to EasyChair. IJCAI-17 workshop held - Aug 19, 2017

Call for Papers

In 2016, retail e-commerce sales worldwide amounted close to 2 trillion US dollars and e-retail revenues are projected to grow to 3.4 trillion US dollars in 2019. However, the rapid transition from the brick-and-mortar shops of old economy is still heavily limited by technology – specifically, the limitations of online product searches, which, especially compared to a conversation with a real world sales associate, return far too many irrelevant and unspecific results to be of reliably convenient use. The key to unlocking the next wave of e-commerce disruption has arrived, this time with the advent of artificial intelligence (AI). We aim to bring the attention of researchers to real problems with AI applications in E-Commerce, ranging from search, recommendation, (re)targeting, information retrieval and natural language processing (NLP) that belong to the regular IT areas, to the business advisory ChatBot belonging to the hot arising areas, etc. In the recent past years, researchers have proposed various AI techniques in the above mentioned application areas. This call focuses on novel methodologies, applications and theories for effectively applying AI in E-Commerce. We encourage submissions on a variety of topics focusing on addressing specific aspects of importance in E-Commerce from AI perspective, including but not limited to: 1. Address theoretical contributions to an established field commonly used in E-Commerce system, or provide that a known problem can be solved in a novel way, e.g., visitor web behavior modeling and visualization, intention and sentiment analysis, recommendation and personalization systems, anomaly or change point detection in streaming data, data cleansing and real time bidding optimization in online advertising. 2. Understanding customers intent from unstructured, customer generated content (queries, reviews). 3. Control / optimization of business metrics via E-Commerce experiences that match customers to products (search, recommendations, advertising). 4. Attribution of customer-generated events / metrics (clicks, conversions, revenue) to specific components of a system (multi-touch attribution problem). 5. Computational economics, Mechanism Design for e-commerce platform using multi-agent learning. 6. ChatBot that can communicate and supply business strategies to online customers and sellers. We encourage submissions of both short papers (at most 3 pages with 1 additional page of reference) and long papers (at most 6 pages with 1 additional page of reference). Accepted short and long papers will be recommended for poster and oral presentations respectively. Please use IJCAI-17's templates, and include author names, affiliations, and email addresses on the first page. Submissions should be made through EasyChair.

Keynote Speakers

Lexing Xie Associate Professor, Computer Science The Australian National University. Title: An Anatomy of Social Media Popularity Abstract: How did a video go viral? Or will it go viral, and when? These are some of the most intriguing yet difficult questions in social media analysis. This talk will first provide a broad overview of recent research in understanding the predicting popularity, driven by larger amounts of online data and more understanding of human perception and psychology. I will then cover a few recent results from my group on understanding and predicting popularity, especially for YouTube videos. I will start by describing a unique longitudinal measurement study on video popularity history, and introduce popularity phases, a novel way to describe the evolution of popularity over time. I will then discuss a physics-inspired stochastic model that connects exogenous stimuli and endogenous responses to explain and forecast popularity. With such novel representation and new models, we can correlate video content type to popularity patterns, make better predictions, describe the endo-exo factors driving popularity, and forecast the effects of promotion campaigns. More Information
Jingrui He Assistant Professor Computer Science and Engineering, CIDSE Arizona State University Title: Learning from Data Heterogeneity: Algorithms and Applications Abstract: In the era of Big Data, data heterogeneity is ubiquitous across multiple application domains, ranging from social network analysis, manufacturing, to healthcare. Data heterogeneity can be present in a variety of forms, such as task heterogeneity, view heterogeneity, instance heterogeneity, label heterogeneity, oracle heterogeneity, etc. In this talk, I will introduce our recent work on addressing data heterogeneity. In particular, I will start with the techniques for modeling a single type of heterogeneity, and then further discuss how to jointly model multiple types of heterogeneity both effectively and efficiently. Finally, I will briefly touch upon the problem of rare category analysis in the presence of data heterogeneity, and demonstrate the performance of the proposed techniques in real applications. More Information
Pingzhong Tang Assistant Professor IIIS, Tsinghua University Title: Large-scale, high-frequency mechanism design, with applications to e-commerce Abstract: In this talk, we will discuss our recent efforts on tackling a type of mechanism design problems that are deployed at large scales and repeated high frequently over time. Typical applications include allocation of buyer impression in e-commerce and sponsored search auction design. The proposed solution is a synthesis of game theory and AI techniques. More Information

Program Committee

Yinghui Xu, renji.xyh@taobao.com, Yinghui Xu is a principal engineer/senior director in Taobao Search Division. He received Ph.D. at Toyohashi university of technology in 2005. In the same year, he joined Ricoh institute of information and communication technology to R&D on cross-media information retrieval, image recognition, natural language processing etc. In 2005, he won the annual Japanese natural language society annual best paper award. In 2008, he won the innovation award for his contribution on patent image retrieval system in Ricoh Group. In 2012,he joined Alibaba group. As one of the key persons in charge of the search technology team,he designed and developed a new generation personalized search and recommendation system with a offline-nearline-online systematic feature. He facilitated the evolution of the search and recommendation intelligent service from offline machine learning to online learning and decision-making learning. Hongxia Yang, yang.yhx@alibaba-inc.com, https://sites.google.com/site/hystatistics/home Hongxia Yang is a Senior Staff Data Scientist/Director in Alibaba Data Technology and Product Division. She received her PhD from Department of Statistics, Duke University in 2010. Her interests span the areas of Bayesian statistics, time series analysis, spatial-temporal modeling, survival analysis, machine learning, data mining and their applications to problems in business analytics and big data. She has been very active in the publication of top conferences, including KDD, AISTATS, ICDM, ICML, etc. She is the Associate Editor of Applied Stochastic Models in Business and Industry and has served as organizers/chairs/program committees for many top machine learning and statistical conferences, including AAAI, KDD, AISTATS, etc. Jun Zhu, dcszj@mail.tsinghua.edu.cn, bigml.cs.tsinghua.edu.cn/~jun/ Jun Zhu is an Associate Professor of Computer Science in Tsinghua University and an Adjunct Faculty in the Machine Learning Department at Carnegie Mellon University (CMU). He received my Ph.D. at Tsinghua in 2009, and did post-doctoral research in the Machine Learning Department at CMU from 2009 to 2011. His research involves both the foundations of statistical learning and the application of machine learning to multi-media data analysis. He has published extensively in the leading conferences on machine learning. He is an Associate Editor at IEEE PAMI. He also served and is serving as area chairs or senior program committee members at the top-tier machine learning conferences, including ICML, NIPS, AISTATS, IJCAI, UAI, and AAAI. He was a local chair to help organize ICML2014, which was held in Beijing. Prof. Zhu was selected as one of the “AI’s 10 to Watch” by IEEE Intelligent Systems, China Computer Federation (CCF) Young Scientist, and was awarded the Excellent Young Scholar Award by NSF China. Martin Ester, ester@cs.sfu.ca, https://www.cs.sfu.ca/~ester/ Martin Ester received a PhD in Computer Science from ETH Zurich, Switzerland, in 1990 with a thesis on knowledge-based systems and logic programming. He has been working for Swissair developing expert systems before he joined University of Munich as an Assistant Professor in 1993. Since November 2001, he has been an Associate Professor, now Full Professor at the School of Computing Science of Simon Fraser University, where he co-directs the Database and Data mining research lab. He has published extensively in the top conferences and journals of his field such as ACM SIGKDD, IEEE ICDM, WWW and ACM RecSys. According to Google Scholar, his publications have received more than 21000 citations, and his H-number is 51. He received the KDD 2014 Test of Time Award for his paper on DBSCAN and RecSys 2010 Best Paper Award. He ranks top 1 at AMiner Most Influential Scholar Annual List 2016. Martin Ester’s current research interests include social network analysis, recommender systems, opinion mining, biological network analysis and high-throughput sequence data analysis. His interests in applications have resulted in various collaborations with research labs, industry and government agencies. He has held tutorials including Aspect-based Opinion Mining in SIGIR 2012 and WWW 2013 and Social Recommendation in ICDM 2011 and RecSys 2013. His services for conference committees include PC-Chair, ACM RecSys 2014, PC Chair, IEEE/ACM ASONAM 2014, Workshop Chair, ASONAM 2013, Senior PC member KDD 2012, 2013, 2014, 2015, 2016, 2017 and Senior PC member RecSys 2013, 2015, 2016. Can Wang, wcan@zju.edu.cn, http://person.zju.edu.cn/en/wangcan Dr. Can Wang is currently an associate professor in the College of Computer Science at Zhejiang University, China. He received the Ph.D. degree and M.S. degree in computer science and B.S. degree in economics from Zhejiang University in 2009, 2003 and 1995 respectively. His research interests include data mining, machine learning etc. He has published over 40 research papers in top journals and international conferences including IEEE Transactions on Knowledge and Data Engineering, IEEE Transactions on Image Processing, Information Science, Pattern Recognition, AAAI, SIGKDD, WWW, ACM Multimedia, SIGIR, CIKM etc. He is the recipient of AAAI Outstanding Paper Award (2012). Meanwhile, he is the coach of ACM/ICPC teams in Zhejiang University. The team he coached won the 35th ACM/ICPC World Final Champion in Orlando, USA in 2011. He served as PC member for KDD 2016. Feijun Jiang, Staff Data Scientist, Alibaba Group. Wei Chu, Senior Staff Engineer, Alibaba Group. Hang Li, Director of Noah's Ark Lab at Huawei Technologies, Hua Wei Group. Pingzhong Tang, Assistant Professor, Director, computational economics lab, Tsinghua University. Jonathan Hosking, Senior Statistician, Amazon Research. Yada Zhu, Research Staff Member, IBM T.J. Watson Research Center. Naoki Abe, Senior Manager, IBM T.J. Watson Research Center. Rui Zhang, Research Staff Member, IBM T.J. Watson Research Center. Hanghang Tong, Assistant Professor, School of Computing, Informatics and Decision Systems Engineering, Arizona State University. Jingrui He, Assistant Professor, School of Computing, Informatics and Decision Systems Engineering, Arizona State University. Quan Lu, Senior Director, Yahoo! Inc. Irwin King, Associate Dean and Professor, Chinese University of Hong Kong. Qiang Yang, Professor of Engineering, Chair Professor and Head of Department of Computer Science and Engineering, Hong Kong University of Science and Technology Hong Kong University of Science and Technology. Bing Liu, Professor, University of Illinois, Chicago. Charles Elkan, Professor, Amazon and UCSD. Ido Guy, Principal Research Engineer , Yahoo Research, Israel. Alexander Tuzhilin, Professor of Information Systems, Stern School of Business, New York University. Bamshad Mobasher, Professor, DePaul University.