Skip to the content.

Welcome to The First International Workshop on Computational Jobs Marketplace to be held as part of The 15th ACM International Conference on Web Search and Data Mining (WSDM 2022).

Want to attend the event? Join with Zoom.

Online job marketplaces such as, CareerBuilder and LinkedIn Inc. have been helping millions of job seekers find their next jobs and thousands of corporations as well as institutions fill their opening positions. Along with the increase of market size, there has been a lot of interesting challenges in this domain, such as the drastic increase of work from home or remote work, the imbalance between the demand and supply of the job market, the popularity of independent workers, the capability of helping job seekers on their whole job seeking journey and career development, the different objectives and behaviors of all major stakeholders in the ecosystem, e.g. job seekers, employers, recruiters and job agents, to name just a few.

This workshop brings academic researchers and industry practitioners together to share early research results. We focus on the state of the art advances in the computational jobs marketplace.



Wenjing Zhang is a Sr Director of Data for Talent Solutions at LinkedIn, where she leads a team of 100+ data scientists and ML engineers across the globe. The work from her team powers the products that millions of people rely on to find a job, learn new skills, and hire the right talent in an efficient and equitable manner. As a veteran in LinkedIn, she has witnessed, initiated, and participated in many transformations through data innovation across consumer and enterprise spaces over the past decade. Prior to LinkedIn, she has worked as a data scientist for several years in eBay and JPMorgan Chase.

Talk Title: Our Journey to #Remote Work.

Talk Abstract: Job changing has dramatically increased since Covid, a phenomenon we call the #GreatReshuffle. This unprecedented moment in the history of has many of us rethink how we work. Working remotely is on employers’ and job seekers’ minds. In this talk, we will present how LinkedIn uses AI and Data Science to adapt to this new trend and our learnings from the journey so far. Given how essential work location is in the job marketplaces, this case study on remote jobs will allow us to peek into our measurement framework and AI system.


Donal McMahon is VP for Data Science at Indeed, and received his PhD in Statistics from Stanford University. He proudly leads Indeed’s Data Platform team, which includes 200 Data Scientists, Data Engineers, Business Intelligence Analysts, Product Managers, and Software Engineers. He’s been “helping people get jobs” at Indeed for the past six years. Previous to this, he worked on Search and Ad ranking problems at Google. He estimates that if Indeed keeps growing at its current rate, we’ll employ over 50% of the world’s workforce by 2040, just after civilization collapses because of the Year 2038 Problem. Until then, though, Donal is going to use math, science and software to help millions of people make smarter, faster and geekier employment decisions.

Talk Title: Unsolved Mysteries in the Online Jobs Marketplace - Unique market characteristics, Open problems and Potential Solution Paths.

Talk Abstract: Online marketplaces have flourished in recent years; as people engage with ride-sharing apps, dating sites and vacation rental platforms. In this session we ask, “what’s unique about the computational labor marketplace?”. We’ll outline differentiating characteristics such as information asymmetry, signal delay, incomplete data, and risk aversion due to high stakes. In addition, macro-economic employment patterns are evolving rapidly. New perspectives are emerging on early/no retirement, remote worki, and secondary gig roles. Covid-19 has accelerated this change. These conditions provide a rich set of novel unsolved problems. We’ll introduce three fundamental challenges we encounter at Indeed, spanning (i) structural missing data patterns, (ii) measurement limitations, and (iii) machine learning model tethering. We’ll discuss partial solution paths, and challenge attendees to contribute in “helping people get jobs”.



Mary Bui-Pham is Vice President, Strategy & Culture at Indeed. She is responsible for driving strategy, business operations, and culture for Indeed’s Business Technology group. Mary is a champion for Indeed’s core value of Inclusion and very passionate about equity in Technology. Previously, Mary served as Vice President of Global Operations for Media Brands & Products at Yahoo where she managed the day-to-day operations of the product development, design, accessibility, and editorial teams responsible for the company’s flagship brands including Yahoo Finance, Yahoo Sports,,, TechCrunch, HuffPost, and many others. Prior to Yahoo, Mary held various leadership positions in Program Management, Business Operations, QA, and Releasement at eBay and DoubleClick. Mary holds a Ph.D. in Chemical Engineering from the University of California, San Diego.

PROGRAM (All Time Slots are in MST)

Time Slot
1:25PM - 1:30PM Opening Remarks
1:30PM - 2:10PM Keynote Talk: Unsolved Mysteries in the Online Jobs Marketplace - Unique market characteristics, Open problems and Potential Solution Paths.
Donal McMahon, VP of Data Science,
2:10PM - 2:25PM A Cross-Platform A/B Testing Framework for Offsite Advertising [PDF]
Shichuan Ma (Indeed), Fengdan Wan (Indeed), Ziying Liu (Indeed), Yu Sun (Indeed) and Haiyan Luo (Indeed)
2:25PM - 2:40PM Learning a 1-dimensional Mapping from State Transitions Data [PDF]
Huichao Xue (LinkedIn), Chao Wang (LinkedIn), Xiaoqing Wang (LinkedIn) and Yan Zhang (LinkedIn)
2:40PM - 2:45PM Break
2:45PM - 3:25PM Keynote Talk
Wenjing Zhang, Senior Director of Talent Solutions, LinkedIn
3:25PM - 3:40PM Pacing Programmatic Job Campaigns by Score-based Ranking [PDF]
Hao Sha (CareerBuilder), Yiyun Zhou (CareerBuilder), Madhav Sigdel (CareerBuilder), Mengshu Liu (CareerBuilder) and Mohammed Korayem (CareerBuilder)
3:40PM - 3:55PM Looking Further into the Future: Career Pathway Prediction [PDF]
Michiharu Yamashita (The Pennsylvania State University), Yunqi Li (Rutgers University), Thanh Tran (Worcester Polytechnic Institute), Yongfeng Zhang (Rutgers University) and Dongwon Lee (The Pennsylvania State University)
2:40PM - 2:45PM Break
4:00PM - 4:55PM Panel Discussion
Host: Mary Bui-Pham, VP of Strategy & Culture,
Panelist: Alexandre Patry, Senior Staff Machine Learning Engineer, LinkedIn
Panelist: Donal McMahon, VP of Data Science,
Panelist: Mohammed Korayem, Senior Director of Data Science, CareerBuilder
Panelist: Hongning Wang, Associate Professor, University of Virginia
4:55PM - 5:00PM Closing Remarks




Liangjie Hong is a Director of Engineering, AI at LinkedIn Inc., managing teams of machine learning engineers and applied researchers to drive AI solutions for Talent Solutions, a core LinkedIn business that connects job seekers and recruiters in a two-sided marketplace. Before that, he was a Director of Engineering at Etsy Inc., leading the overall data science and machine learning efforts across search, recommendation and advertising. Previously, he was Senior Manager of Research at Yahoo Research, leading science efforts for Personalization and Search Sciences. Liangjie has given numerous technical talks at academic conferences as well as industrial meetings. He also co-founded User Engagement Optimization Workshop which has been held in conjunction with CIKM 2013 and KDD 2014. In addition, he was a co-instructor for a tutorial on Online User Engagement: Metrics and Optimization, which has part of WSDM 2018, WWW 2019 and KDD 2020. Liangjie has extensively published papers in recommender systems, search, causal inference and other applied machine learning domains. He has served as senior or program committee members on all major applied machine learning and data mining conferences including KDD, WSDM, WWW, SIGIR, CIKM, EMNLP and ICML.


Mohammed Korayem is a Senior Director of Data Science at CareerBuilder, where he leads the R&D data science and data engineering teams focused on search, recommendation and AI solutions across the products. His research interests search and recommendation, large-scale visual and textual mining, machine learning, deep learning, computer vision, and soft computing. His research published in WWW, KDD, ACL, ICWSM, NDSS, AAAI, etc. His research covered in media including New Scientist Magazine, MIT Technology Review, Communications of the ACM website, etc. His team received The American Business Awards in Artificial Intelligence/Machine Learning Solutions category for industry-first AI Resume Builder. He obtained his Ph.D. and M.Sc. in Computer Science from Indiana University. He holds multiple patents. He co-organized multiple workshops and conferences including KDD-ORAS: Online and Adaptative Recommender Systems (OARS) and Southern Data Science Conference.


Haiyan Luo is a Director of Engineering at for its display advertising business, where he currently leads a world wide group of 60+ software engineers, data scientists and engineering managers. Previously, he worked at LinkedIn, Yahoo, Cisco and Bell Labs. He received his Ph.D. from the University of Nebraska-Lincoln. He published 40+ academic papers and 10+ patents and several books. He is a IEEE senior member. He also served as the chair or a TPC member of numerous international magazines and conference papers such as IEEE INFOCOM, IEEE SECON etc. He founded or co-founded several startups. His specialty includes digital advertising, big data systems, recommender systems, financial risk analysis, sponsored content etc.



We solicit papers describing significant and innovative research and applications to the field of job marketplaces. We invite submissions on a wide range of topics, spanning both theoretical and practical research and applications. Topics include but not limited to:



Following the WSDM 2022 main conference review process, each paper will be reviewed by at least three PC members. The acceptance decisions will take in account novelty, technical depth and quality, insightfulness, depth, elegance, practical or theoretical impact, reproducibility and presentation. We will use double-blind reviewing. For each accepted paper, at least one author must attend the workshop and present the paper.

Please refer to the WSDM website for the policies of Conflict of Interest, Violations of Originality, and Dual Submission:

Submissions are limited to a total of FIVE pages, including all content and references, must be in PDF format, and formatted according to the new Standard ACM Conference Proceedings Template. Additional information about formatting and style files is available here.

Papers can be submitted through EasyChair.

All accepted papers will be archived on the workshop website.


Please contact organizers with any questions and concerns: