Data mining has been a trending research area with contributions from diverse communities including computer scientists, statisticians, mathematicians, and researchers working on data-intensive problems. While most data mining methodologies are developed for general problem settings, such as unsupervised learning and supervised learning, (1) there are many factors and challenges such as socioeconomic, organizational, human-centered and cultural aspects rarely explored; (2) there are also specific domain knowledge, factors and challenges in developing data mining solutions for a specific domain or a novel real-world application; and (3) a critical challenge facing existing data mining is to discover actionable knowledge that can directly support decision-making tasks. Due to the need of incorporating such domain knowledge, factors and challenges in the data mining process, the challenge to discover actionable knowledge hidden in complex data, and the lack of both general and customized algorithms and tools, domain driven data mining presents many significant challenges and opportunities for transforming data mining to actionable knowledge discovery and for delivering actionable insights and intelligence for solving general and specific domain-driven problems. This special issue aims to call for the latest theoretical and practical developments, expert opinions on the open challenges, lessons learned, and best practices in domain driven data mining.

Indeed, Domain-Driven Data Mining has attracted significant attention from both academic and industry. There have been a workshop series on domain driven data mining during 2007-2011 with ICDM which has been competitively ranked in the Australia CORE conference rank, a special issue with TKDE, and several tutorials delivered. Given that the previous activities were mostly 10 years ago, there are various new research problems and challenges following the recent advances in the last decade. Building upon these prior works, we aim to foster further discussions on broad general and specific domain challenges, the incorporation of domain knowledge into data mining processes and models, especially methodologies and tools newly developed in the last decade, such as deep neural networks, graph embedding, text mining, and reinforcement learning.

This workshop will be part of SDM 2021. Domain-driven data mining is an important research in SDM given the highly applied and interdisciplinary nature of the conference. In order for data mining algorithms to achieve superior performance in significant business and societal problems, it is necessary to incorporate domain knowledge to guide the model and algorithm design.

Accepted papers/presentations can be further reviewed for journal publications:

Recent Studies on Domain-Driven Data Mining with the International Journal of Data Science and Analytics
Data-Intensive Research in Ecommerce with the journal of Electronic Commerce Research and Applications
Data-Driven Investment Strategies with the journal of Frontiers in Artificial Intelligence

More information: https://datascience.utk.edu/content/dddm/