The UW–Madison Data Science Institute (DSI), powered by American Family Insurance, announced ten research projects selected for funding through a unique sponsored research partnership.
American Family Insurance has committed $10 million over 10 years to the American Family Funding Initiative, which supports UW–Madison research with potential to fuel discovery in data science while creating value for industry. Since its launch in spring 2020, thirty-five teams of UW–Madison faculty and collaborators have been awarded nearly five million dollars through this initiative.
“The projects selected in Round 5 have important industry applications, and they also hold great promise to advance the field of data science,” says Kyle Cranmer, David R. Anderson Director of the Data Science Institute. “I am a firm believer in use-inspired research and the tenet that the unique challenges of a particular application are an effective way to inspire fundamental advances.”
Funds are awarded through a competitive application process administered by DSI, and American Family Insurance provides selected projects with both funding and collaboration with their data scientists. Both organizations evaluate applications on their novelty, potential impact to data science and alignment with topics of interest to American Family.
In Round 5, enhanced engagement with applicants, including an in-person Town Hall meeting and insurance presentations from American Family business leaders, resulted in an exceptionally strong pool of applications.
“Round 5 has been a great and transformative experience,” says Neal Silbert, Auto Product Predictive Analytics AVP at American Family Insurance. “We built on our learnings from the prior four rounds to develop a stronger sense of community, developed closer connections with prospective principal investigators, and focused on communicating leading areas of academic interest and business impact. This led to a dramatic increase in research proposals that are both scientifically interesting and hold high promise to solve important insurance analytic challenges.”
A sixth round of funding will be announced in January 2024. Project summaries and PI bios are available at the data science @ uw website.
American Family Funding Initiative Round 5 Awards:
3D Scanning and Machine Learning for Comprehensive Property Inspection
PI: Joao Dorea, Assistant Professor, Department of Animal and Dairy Sciences
Learning what is Relevant for Counterfactual Policy Evaluation
PI: Josiah Hanna, Assistant Professor, Department of Computer Sciences
Improving Auto-labeling with Confidence Functions
PI: Ramya Korlakai Vinayak, Assistant Professor, Department of Electrical and Computer Engineering; Co-PI: Fred Sala, Assistant Professor, Department of Computer Sciences
Detecting AI-altered Images to Combat Claims Fraud
PI: Yong Jae Lee, Associate Professor, Department of Computer Sciences
Supervised Sequence Analysis for High-Dimensional Discovery of Predictive Histories for Health and Economic Outcomes
PI: Adeline Lo, Assistant Professor, Department of Political Science; Co-PI: Héctor Pifarré i Arolas, Assistant Professor, La Follette School of Public Affairs
Behavioral Analytics for Personalized Safer Driving
PI: Yonatan Mintz, Assistant Professor, Department of Industrial and Systems Engineering
Reliable and Scalable Shapley Value Estimation for Interpretable ML
PI: Garvesh Raskutti, Associate Professor, Department of Statistics
Data-Efficient Customization for Large Pretrained Models
PI: Fred Sala, Assistant Professor, Department of Computer Sciences
New Joint Modeling Approach for Risk Assessment of Digital Medical Records
PI: Raj Veeramani, Professor, College of Engineering and School of Business; Co-PI: Shiyu Zhou, Professor, Department of Industrial and Systems Engineering
ELSA: Efficient Label Shift Adaptation for Accurate Claim Fraud Detection
PI: Jiwei Zhao, Associate Professor, Department of Biostatistics and Medical Informatics