Hima Lakkaraju of Harvard University joined us on April 11, 2022, for “Does Model Understanding Improve Human Decision Making?”
As machine learning (ML) models are increasingly being employed to make consequential decisions in high-stakes settings such as finance, healthcare, and hiring, it becomes important to ensure that these models are actually beneficial to human decision makers.
To this end, recent research in ML has focused on developing techniques which aim to explain complex models to domain experts/decision makers so that they can determine if, when, and how much to rely on the predictions of these models.
In this talk, I will give a brief overview of the state-of-the-art in explaining ML models, and then present some of our recent research on understanding the impact of explaining the rationale behind model predictions to decision makers.
More specifically, I will discuss two user studies that we carried out with domain experts in healthcare (e.g., doctors) and hiring (e.g., recruiters) settings where we analyzed the impact of explaining the rationale behind model predictions on the accuracy and the discriminatory biases in the decision making process.
Himabindu “Hima” Lakkaraju is an Assistant Professor of Business Administration at Harvard Business School. She is also a faculty affiliate in the Department of Computer Science at Harvard University, the Harvard Data Science Initiative, Center for Research on Computation and Society, and the Laboratory of Innovation Science at Harvard. She teaches the first year course on Technology and Operations Management, and has previously offered multiple courses and guest lectures on a diverse set of topics pertaining to Artificial Intelligence (AI) and Machine Learning (ML), and their real world implications.
Professor Lakkaraju’s research focuses on the algorithmic, practical, and ethical implications of deploying AI models in domains involving high-stakes decisions such as healthcare, business, and policy. More specifically, she studies the design and deployment of AI models that are explainable (readily understandable to decision makers), fair (do not discriminate against minority groups), and more broadly reliable when deployed in the real world. She leads the AI4LIFE research group at Harvard University as part of which she supervises multiple postdoctoral, graduate, and undergraduate students. Professor Lakkaraju’s research has been published in top AI and ML conferences including the International Conference on Machine Learning (ICML), Advances in Neural Information Processing Systems (NeurIPS), the AAAI Conference on Artificial Intelligence, and International Conference on Artificial Intelligence and Statistics (AISTATS), as well as prestigious interdisciplinary journals such as Quarterly Journal of Economics (QJE).
Her research has been felicitated with multiple best paper awards including the INFORMS Best Data Mining Paper Prize and the SIAM International Conference on Data Mining (SDM) Best Research Paper Award. She also received prestigious grants from the National Science Foundation (NSF), and various research awards from Google, Amazon, and Bayer. Her research has also been covered by various popular media outlets including the New York Times, MIT Tech Review, Harvard Business Review, TIME magazine, Forbes, Wired, and VentureBeat. Professor Lakkaraju was also named one of the world’s top Innovators Under 35 by both Vanity Fair and the MIT Technology Review.
In addition to her research, she is passionate about advising startups in the space of AI/ML, and making the field of AI/ML more accessible to the general public. She advises the research and product strategy of Fiddler AI, one of the most sought after startups in the field of responsible AI. Professor Lakkaraju also co-founded the Trustworthy ML Initiative (TrustML) to lower entry barriers, promote discussion and debate on latest developments, and build a community of researchers, practitioners, and policy makers working on AI and its real world implications. As part of this initiative, Lakkaraju has developed various accessible, publicly and freely available tutorials on several aspects of AI and ML. She has also started a virtual talk series where renowned experts (both in AI/ML and other domains such as healthcare, business, and policy) discuss their research and anyone in the world can attend these talks and interact with these experts.
Professor Lakkaraju received her PhD and MS degrees in computer science from Stanford University. Prior to her stint at Harvard Business School, she has held various positions at Microsoft Research, IBM Research, and Adobe.