KDD is the premier Data Science conference. We invite original technical research contributions in all aspects of the data science lifecycle including but not limited to: data cleaning and preparation, data transformation, mining, inference, learning, explainability, data privacy, and dissemination of results. Technical data science contributions that advance United Nations Sustainable Development Goals (SDGs) are also encouraged. This year we are also inviting paper submissions that are at the intersection of data science and society as part of the research track.

Data Cleaning and Preparation: A significant part of the data science lifecycle is spent on data cleaning and preparation. In several domains, data cleaning tasks continue to be rule-based and are often brittle, i.e., they break down in face of a constantly changing and evolving environment. Learning-based approaches for data cleaning and preparation which are generalizable and adaptive across domains are highly sought.

Data Transformation and Integration: The process of mapping data from one representation into another is at the heart of data science. The mapping can be query driven, based on a statistical task, or might involve integrating data from myriad sources. We seek original contributions that address the trade-off between the complexity of the transformation and algorithmic efficiency.

Mining, Inference, and Learning: These topics are the kernel of knowledge discovery from databases (KDD) paradigm and continue to witness massive growth. While classical aspects of supervised learning have been mainstreamed into the development cycle, new variations on unsupervised learning like self-supervision, few shot learning, prescriptive learning (reinforcement learning), transfer learning, meta learning, and representational learning are pushing the research boundary in a world where the proportion of labeled and annotated data is becoming minuscule. In each of these topics, we seek submissions that highlight the trade-off between accuracy, stability, robustness, and efficiency. Submissions that propose “new” inference tasks are strongly encouraged.

Explainability: As data science models are becoming part of daily human activity there is a need, often being expressed in law, that the models be fair, interpretable, and provide mechanisms to explain how a prediction or decision by the model was arrived at. Interpretable models will lead to their wider acceptance in society at large and increase the value of Data Science as a discipline in its own right.

Data Privacy and Ethics: Data privacy or lack thereof, continues to be the achilles heel of the whole data science enterprise. We seek technical contributions that advance the state of data science methods while guaranteeing individual privacy, respect for societal norms and ethical integrity.

Model Dissemination: Migrating a data science model from a research lab to a real-world deployment is non-trivial and potentially a continuous ongoing process. We seek research submissions that highlight and address technical and behavioral challenges during model deployment, feedback, and upgradation.

Data Science and Society: Data science has a critical role to play in addressing grand societal challenges, whether in addressing health inequities, climate change, resilience, sustainability, early childhood development, poverty, or other related areas. Success of data science in such areas is not just a function of data science alone, but it also requires careful engagement with the stakeholder, working across disciplines, and translation of the data science innovation towards achieving a societal impact. We invite papers that are at this interface, papers that demonstrate interdisciplinarity, papers that demonstrate stakeholder engagement, and papers that demonstrate a plan for realization of the data science application through translation. The innovation of these works may not be in the novelty of a data science method; rather, the innovation of these works will be at the careful exposition of societal challenge, and the role that data science and interdisciplinarity played towards addressing the societal challenge. The papers will be evaluated with this context. It is expected that papers have authors from different disciplines, and carefully situate the problem statement that is being solved, the role of data science, and societal impact evaluation.