Welcome to The AAAI Workshop on Computational Jobs Marketplace to be held as part of The 39th Annual AAAI Conference on Artificial Intelligence.

Online job marketplaces such as Indeed.com, ZipRecruiter, CareerBuilder and LinkedIn Inc. help millions of job seekers find their next job. These platforms also provide services for thousands of employers to fill their opening positions. With all players in the ecosystem, the market size of this industry is projected to steadily grow and reach $43 billion dollars in 2027. On top of that, the global pandemic COVID-19 in 2020 and the emerging AI trends have profoundly transformed workplaces and the online jobs marketplace, creating and driving new types of jobs and marketplace technologies around the world. Today, online job marketplaces play a central role in this new wave of digital revolution of workforce and workplaces. While this industry generates tremendous growth in the past several years, technological innovations around this industry have yet to come. Many technologies, such as search systems, recommender systems as well as advertising systems that the industry heavily relies on are deeply rooted in their more generic counterparts, which may not address the unique challenges in this industry for better products serving both job seekers and employers/recruiters.

This workshop would play a critical role to bring together the research and development community in this industry especially around data science and machine learning and facilitate innovations on theories, models, systems and practices in this currently scattered community. An expected outcome of the workshop is to create awareness of this emerging industry with its technological opportunities and challenges, which might foster future research and development, creating novel products to serve future job seekers and employers/recruiters.

KEYNOTE SPEAKERS

daniel

Daniel Hewlett, Principal Staff AI Engineer at LinkedIn

Talk Title: Emerging Challenges for Recruiting AI

Abstract: This talk will explore some of the ways that the AI problems at the core of the talent marketplace are changing, opening up new areas of research and application. Using the ongoing evolution of LinkedIn’s Recruiter product experience from a classical search engine to a hiring assistant as a case study, we will examine some of these newer AI problems, relate them to other academic research areas, and discuss how the community can collaborate and share knowledge going forward.

Short Bio: Daniel Hewlett is a Principal Staff AI Engineer at LinkedIn, focused on developing the AI capabilities underlying LinkedIn’s new Hiring Assistant, an agent supporting the needs of hirers within the talent marketplace. Previously, Daniel worked in the NLP group at Google Research, and at YouTube, after receiving his Ph.D. in Computer Science from the University of Arizona in 2011. Daniel has contributed to publications at conferences including AAAI, ACL, and KDD.

hasan

Mohammad Al Hasan, Professor of Computer Science at Indianna University

Talk Title: Ordered Network Embedding and its Potential Applications in Online Job Marketplaces

Abstract: Node embedding is a well-studied research topic with numerous proposed methods derived from matrix factorization to graph neural networks. All the proposed methods attempt to preserve pairwise node proximity in the embedding space, where the proximity is measured based on graph topology or node features. The proximity metrics are generally symmetric, which limits the existing methods to consider undirected networks only. However, in real-life many networks are ordered, and existing embedding methods are not good fit for representing nodes of such networks. For instance, in the job marketplace domain, we use job transition network to generate future job recommendation, but a job transition network is directional, and ignoring such direction for embedding the job vectors may generate poor job recommendation. In this talk, I will give a brief overview of existing methodologies of ordered network embedding followed by a presentation of BINDER, a very efficient method for embedding ordered networks that we have proposed.

Short Bio: Dr. Mohammad Al Hasan is a full Professor of Computer Science at Luddy School of Informatics, Computing, and Engineering, Indiana University Indianapolis. Before joining academia, he was a senior research scientist at eBay Research Labs in San Jose, CA. He received his Ph.D. from the Computer Science department at Rensselaer Polytechnic Institute (RPI), NY. Dr. Hasan holds an MS degree in Computer Science from the University of Minnesota, Twin Cities. His core research interest lies in graph machine learning, and natural language processing with broader interests spanning data mining, bioinformatics, biomedical informatics, network analysis, information retrieval, and social network analysis. His research has garnered support from prestigious organizations such as NSF, NIH, and eBay Inc. In recognition of his contributions, Dr. Hasan received several awards, including the NSF Career Award and SIGKDD dissertation award. He is a Senior Member of ACM and IEEE.

PROGRAM

Time Content
8:55 AM – 9:00 AM Opening Remarks from Chairs
9:00 AM – 9:45 AM Keynote Talk: Daniel Hewlett from LinkedIn
Talk Title: Emerging Challenges for Recruiting AI
9:45 AM – 9:55 AM Talk: Trading off Relevance and Revenue in the Jobs Marketplace: Estimation, Optimization and Auction Design [PDF]
Farzad Pourbabaee (LinkedIn), Sophie Yanying Sheng (LinkedIn), Peter B. McCrory (LinkedIn), Luke Simon (LinkedIn), Di Mo (LinkedIn)
9:55 AM – 10:05 AM Talk: Mitigating Language Bias in Cross-Lingual Job Retrieval: A Recruitment Platform Perspective [PDF]
Napat Laosaengpha (Chulalongkorn University), Thanit Tativannarat (Chulalongkorn University), Attapol Rutherford (Chulalongkorn University), Ekapol Chuangsuwanich (Chulalongkorn University)
10:05 AM – 10:15 AM Talk: Multi-objective ranking for job marketplace optimization [PDF]
Rong Liu (ZipRecruiter), Eran Brill (ZipRecruiter), Ethan Barker (ZipRecruiter), Ashley Chang (ZipRecruiter), Yiftach Dayan (ZipRecruiter), Yu Sun (ZipRecruiter)
10:15 AM – 10:25 AM Talk: Enterprise Experimentation with Hierarchical Entities [PDF]
Shan Ba (LinkedIn), Shilpa Garg (LinkedIn), Jitendra Agarwal (LinkedIn), Hanyue Zhao (LinkedIn)
10:25 AM – 10:35 AM Talk: Lessons Learned — Building ML Models to Remove Irrelevant Results in Job Search [PDF]
Gabriel Womark (ZipRecruiter), Ritvik Kharkar (ZipRecruiter), Ishan Shrivastava (ZipRecruiter)
10:35 AM – 11:20 AM Keynote Talk: Mohammad Al Hasan from Indiana University
Talk Title: Ordered Network Embedding and its Potential Applications in Online Job Marketplaces
11:20 AM - 11:30 AM Talk: Weak Supervision For Improved Precision In Search Systems [PDF]
Sriram Vasudevan (LinkedIn)
11:30 AM – 11:40 AM Talk: Harnessing Large Language Models for Cost-Effective Relevance Labeling in Job Search Systems [PDF]
Ishan Shrivastava (ZipRecruiter), Nadav Barkai (ZipRecruiter), Ritvik Kharkar (ZipRecruiter)
11:40 AM – 11:50 AM Talk: Migrating a Job Search Relevance Function [PDF]
Bennett Mountain (ZipRecruiter), Gabriel Womark (ZipRecruiter), Ritvik Kharkar (ZipRecruiter)
11:50 AM – 12:00 PM Talk: Ordinal Regression for Job Search Keyword Similarity Prediction [PDF]
Md Ahsanul Kabir (CareerBuilder), Kareem Abdelfatah (CareerBuilder), Mohammed Korayem (CareerBuilder), Mohammad Hasan (Indiana University)
12:05 PM – 12:10 PM Closing Remarks from Chairs

ORGANIZERS

Liangjie

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. Prior to Yahoo Research, he obtained his PhD in Computer Science from Lehigh University. 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

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\footnote{https://www.southerndatascience.com/}.

Haiyan

Haiyan Luo is a VP of Engineering at ZipRecruiter, where he currently leads a world wide group of software engineers, data scientists and engineering managers. Previously, he worked at Indeed, 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 organzier, chair or a TPC member of numerous international magazines, conference and workshhop papers such as KDD, WSDM, INFOCOM, 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.

PROGRAM COMMITTEE MEMBERS

LIST OF TOPICS

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:

IMPORTANT DATES

SUBMISSION DETAILS

Following the AAAI 2025 main conference submission & review process, each paper will be reviewed by 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.

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

Please submit your paper via Open Review site.

CONTACTS

Please contact organizers with any questions and concerns:

ARCHIVES

Previous editions of the workshop are listed here: