Multi-Armed Bandits and Reinforcement Learning: Advancing Decision Making in E-Commerce and Beyond
in conjunction with KDD 2023
August 7th, 2023
Location: Long Beach, CA
https://sites.google.com/view/marblekdd-2023/
Submission Deadline: June 6, 2023 (Everywhere on earth)
Acceptance Notification: June 23, 2023
Call for Participation
Reinforcement learning (RL) and multi-armed bandits (MAB) have been powering e-Commerce and other industrial applications since the early days of the field. Today, MAB and RL already play a significant role in e-commerce tasks, including product search, recommender systems, advertising, pricing, among many other tasks. With the exploding popularity of stochastic optimization and decision making under uncertainty, RL and MAB researches are poised to transform e-commerce once again, but requires a forum where new and unfinished ideas could be discussed. This workshop aims to stimulate discussions, especially those at the boundaries between computer science, marketing science, operations research, statistics, and econometrics, and bringing together researchers from academia and frontline practitioners. Professors and students in universities, researchers from research labs and tech companies, applied scientists, and machine learning engineers from the industry are all potential audiences and participants.
Specifically, and not exclusively, we invite research contributions in different formats:
- Original research papers
- Vision, opinion, and position papers
- System Demonstrations
- Extended abstracts for talks or panel discussion proposals
Original research papers
Original research papers are solicited for the following set of non-exhaustive topics:
- Theories and applications of reinforcement learning and multi-armed bandits
- Recommender systems and product suggestions, semantic recommendation
- Search and product query auto-completion
- Supply-chain optimization
- Fraud and spam detection in e-commerce
- Computational advertising
- Deep reinforcement learning for microeconomics theory
- Multi-armed bandits for online advertising and pricing
- Contextual MAB for personalized dynamic recommendations
Additionally, we also encourage topics from the following areas:
- ML applications in e-commerce and industries
- AI chatbot voice-mining for promo and recommendations
- AI for ad creatives and publishers
- AI algorithm bias, interpretable ML
- Shopping assistants, agents, and chat bots
- E-commerce related social media processing
- ML applications in web search, question answering, personalization
Vision, Opinion, and Position Papers
We will also welcome vision, opinion and position papers that provide discussions on challenges and roadmaps (for MAB or RL centric systems, applications and emerging models for e-commerce and product data).
System Demonstrations
We encourage system demonstration papers dedicated to illustrating how MAB or RL systems are designed, implemented, maintained. Related topics include:
- Design and implementation of scalable RL or MAB systems
- Data and privacy protection
- Addressing bias and vulnerabilities in deployed systems
- Improving the reliability of deployed systems
Extended Abstracts
The extended abstract should clearly explain the motivation, research problem, methodology, results and contributions.
Submission Directions
Submissions may take the form of long papers (without length restrictions), short papers (3-8 pages), and extended abstracts (1-2 pages), including all content and references, and must be in PDF format and formatted according to the new Standard ACM Conference Proceedings Template. Papers that do not meet the formatting requirements will be rejected without review. The accepted papers will be published online and will not be considered archival. Proceedings will be available for download after the conference. We are using the CMT system for submissions. Please submit your paper using this link.
Review Process: Each full paper will be reviewed by two to three PC members, while extended abstracts will not be reviewed. We will use double-blind reviewing. For each accepted paper, at least one author must attend the workshop and present the paper.
Organizers
Daniel Jiang, Research Scientist, Facebook Core Data Science
Haipeng Luo, Associate Professor, Computer Science Department, University of Southern California
Chu Wang, Applied Science Manager, Sponsored Ads, Amazon
Yingfei Wang, Assistant Professor, Foster School of Business, University of Washington
Zeyu Zheng, Assistant Professor, IEOR, University of California, Berkeley & Amazon
Jinghai He, PhD student, IEOR, University of California, Berkeley
For questions, contact marble-kdd@googlegroups.com
------------------------------
Yingfei Wang
Assistant Professor
University of Washington
Seattle WA
------------------------------