The goal of this research is to create and explore novel methods for detection of emerging events in massive, complex real-world datasets. The approach consists of new algorithms to efficiently and exactly find the most anomalous subsets of a large, high-dimensional dataset, as well as methodological advances to incorporate incremental model learning from user feedback into event detection, incorporate society-scale data from emerging, transformative technologies such as cellular phones and user-generated web content, and augment event detection by creating methods and tools for event characterization, explanation, visualization, investigation and response.
The experimental research is integrated with a multi-pronged educational initiative to incorporate machine learning into the public policy curriculum through development of courses and seminars, workshops in machine learning and policy research and education, and establishment of a new Joint Ph.D. Program in Machine Learning and Policy. The results of this project will be incorporated into deployed event surveillance systems and applied to the public health, law enforcement, and health care domains, enabling more timely and accurate detection of emerging outbreaks of disease, prediction of emerging hot-spots of violent crime, and identification of anomalous patterns of patient care. Project results, including publications, software, and datasets, will be disseminated via project web site (www.cs.cmu.edu/~neill/CAREER).