Recommendation systems are used widely in ecommerce industries, multimedia content platforms and social networks to provide suggestions that a user will most likely consume or connect; thus, improving the user experience. This motivates people in both industry and research organizations to focus on personalization or recommendation algorithms, which has resulted in a plethora of research papers. While academic research mostly focuses on the performance of recommendation algorithms in terms of ranking quality or accuracy, it often neglects key factors that impact how a recommendation system will perform in a real-world environment. These key factors include but are not limited to: business metric definition and evaluation, recommendation quality control, data and model scalability, model interpretability, model robustness and fairness, and resource limitations, such as budget on computing and memory resources, engineering workforce cost, etc..
The gap in constraints and requirements between academic research and industry limits the broad applicability of many of academia’s contributions for industrial recommendation systems. This workshop aspires to bridge this gap by bringing together researchers from both academia and industry. Its goal is to serve as a platform via which academic researchers become aware of the additional factors that may affect the chances of algorithm adoption into real production systems, and the performance of the algorithms if deployed. Industrial researchers will also benefit from sharing the practical frameworks at an industrial level.
May 20, 2021 : Workshop paper submission
June 10, 2021: Workshop paper notifications
July 10, 2021: Camera-ready deadline for workshop papers
August 14, 2021: Workshop Date
Call For Papers
This workshop welcomes submissions from researchers and industrial practitioners broadly related to recommendation systems, such as novel recommendation models, efficient recommendation algorithms, novel industrial frameworks, etc. In order to emphasize the gap between the two communities, we extremely welcome submissions on industrial recommendation system infrastructures based on given resources, models and algorithms supported by the specific infrastructures, and frameworks or end-to-end systems that have been deployed in real world production. All accepted papers will be posted on the workshop website and will not appear in the KDD proceedings. Selected papers will be presented as contributed talks.
Specific topics of interest are including but not limited to:
- Frameworks or end-to-end systems from industry are extremely welcomed.
- Novel data mining and machine learning algorithms for scalable Recommender systems.
- Personalization, including personalized product recommendation, streaming content recommendation, ads recommendation, news and article recommendation, etc.
- New applications related to recommendation systems.
- Existing or novel infrastructures for recommendation systems.
- Interactive recommendation system.
- Explainability of recommendations.
- Fairness, privacy and security in recommender systems.
- Recommendations under multi-objective and constraints.
- Reproducibility of models and evaluation metrics.
- Unbiased recommendation.
- User research studies on real-world recommender systems.
- Business impact of recommendation systems.
The workshop accepts long papers (limited to 9 pages), short papers (6 pages), posters (4 pages), abstracts and demos (2 pages). Paper submission and reviewing will be following the directions of the KDD main conference. Reviews are not double-blind, and author names and affiliations should be listed. Submissions should include all content and references within the limited pages, and must be in PDF format and formatted according to the new Standard ACM Conference Proceedings Template. For LaTeX users: unzip acmart.zip, make, and use sample-sigconf.tex as a template. Additional information about formatting and style files is available online at: https://www.acm.org/publications/proceedings-template. Papers that do not meet the formatting requirements will be rejected without review. In addition, authors can provide an optional two (2) page supplement at the end of their submitted paper (it needs to be in the same PDF file) focused on reproducibility.