Call for Applied Data Science Track Papers
Call for Applied Data Science Track Papers
- Paper Submission: Feb 8th, 2021
- Final Notification: May 17th, 2021
- Camera-ready: June 17th, 2021
- Video Presentation and Presentation Slides (Required): July 12th, 2021
- Conference: August 14-18, 2021
All deadlines are at 11:59 PM anytime in the world.
We solicit submissions of papers describing designs and implementations of solutions and systems for practical tasks in data mining, data analytics, data science, and applied machine learning. The primary emphasis is on papers that either solve or advance the understanding of issues related to deploying data science technologies in the real world. Papers demonstrating significant, verifiable business- or real-world impact as a result of such deployments are encouraged. For details, please go over the Requirement section below.
The topics of submissions include data-science applications in all mature and emerging domains, as well as contributions to enabling algorithmic, infrastructure, and optimization methodologies to improve learning efficiency, scaling, and adoption/deployment.
- Data protection
- Design of experiments
- Interpretable models
- Addressing bias in deployed systems
- Addressing vulnerabilities in the on-field deployment
- Improving the reliability of deployed systems
- Privacy-sensitive applications of learning systems
- Ethical consideration in applications
- Applications involving explainable aspects of algorithms
- Validation and verification approaches for learning systems
- Applications that support broader goals on sustainability, equitability, bias-reduction, social justice, and social good
The Applied Data Science Track is distinct from the Research Track in that submissions focus on applied work addressing real-world problems and systems demonstrating tangible impact/value in their respective domains (e.g., industries, government initiatives, social programs). Please note that papers that do not satisfy the requirements (e.g., a research track paper) might be rejected without a formal review.
A paper in the Applied Data Science Track may fall into two major categories, Deployed and Evidential.
Category DEPLOYED: Must describe an implementation of a system that solves a significant real-world problem and is (or was) in production use for an extended period. The paper should present the problem, its significance to the application domain, the decisions and tradeoffs made when making design choices for the solution, the deployment challenges, and the lessons learned from successes and failures. Evidence must be provided that the solution has been deployed by quantifying post-launch performance. Papers that describe enabling infrastructure for large-scale deployment of applied machine learning also fall in this category. An example might be a deployed system that collects heartbeat audio from mobile phones during a marathon race and uses machine learning to identify potentially irregular heartbeat signals and alert support personnel. The work may particularly focus on how to overcome challenges in data collection, low-resource processing, and usability, and it is perfectly fine that the underlying machine learning algorithms are not fundamentally groundbreaking.
Category EVIDENTIAL: Must describe fundamental insights derived from addressing a significant real-world problem, even though a system has not been deployed. This might include papers providing significant gains in the understanding of an applied area/domain (for example, involving data or system deployment needs) or even papers where a conclusion has been reached that the problem is unsolvable. In addition to insights, the paper must explain what milestones were reached, what the practical impact is, and (if applicable) what the obstacles to deployment are. Straightforward improvements over trivial baseline solutions are unlikely to qualify. Continuing the example above, a paper in this category might present a system that achieves reasonable error rates in an experiment with many volunteers but suffers from interferences among mobiles that are located very close to each other.
Besides common requirements such as impact, clarity of presentation, reproducibility, we require that a submission specifies an audience or a group of users that have benefited or will benefit from the solution presented in the submission. In particular, the focus of novelty for an ADS submission is different from that of a Research Track submission in the sense that we focus more on business novelty, engineering novelty, usability, and user experience novelty, and whether the work provides significant gains in the understanding in an applied domain, etc.
KDD is a dual track conference hosting both a Research track and an Applied Data Science track. Due to a large number of submissions, papers submitted to the Research track will not be considered for publication in the Applied Data Science track and vice versa. Authors must read the track descriptions carefully and choose an appropriate track for their submissions.Submissions to the Applied Data Science track is *single*-blind (author names and affiliations should be listed). Papers that have been presented as technical reports with listed authors will not be considered for review. An exception to the rule is the papers that have been submitted to arXiv at least one month prior to the deadline (January 8th, 2021). Authors can submit these papers but with a different title and abstract. Papers that appear in arXiv after Jan 8th, 2021 until the end of the review process will not be accepted.
Submissions are limited to a total of nine (9) pages, including all content and references, and must be in PDF format. 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 and start at page 10) focused on reproducibility (see reproducibility section for more details. After the submission deadline, authors are not allowed to add additional authors to the submitted papers.
Website for submissions: https://cmt3.research.microsoft.com/KDD2021
Haixun Wang, Instacart
Iryna Skrypnyk, EVERSANA