Join us in welcoming Mo Liu, assistant professor from NC State’s Department of Statistics, as he discusses decision-focused optimization. Alums and friends of the program are always welcome.
Don’t worry. We recorded the event
Access Password: *O2?dHr=
Value of One Data Point: Active Label Acquisition in Decision-Focused Learning
Decision-focused learning refers to machine learning methods that consider the downstream decision-making problem when designing and training prediction models. When building such a prediction model, using informative data can significantly reduce the expected loss from suboptimal decisions induced by the model.
This talk will introduce a sequential data collection method that iteratively gathers informative data within the decision-focused learning framework. It will first review recent developments in decision-focused learning and then focus on the personalized assortment optimization problem.
We introduce a novel concept, the ‘value of one data point,’ which evaluates the marginal contribution of acquiring a specific customer’s preference to the expected revenue in personalized assortment optimization, given the existing training set. Notably, this value drops to zero once the optimal assortment for this specific customer is determined. To estimate this value and identify important customers for acquiring their preferences, we derive a feature-dependent upper bound. This bound provides significant insights into the importance of each data point for revenue growth. Based on this upper bound, we develop a personalized incentive policy for effectively collecting survey data from customers to obtain their preferences. Theoretically, we show that our personalized incentive policy requires smaller cumulative incentives than any fixed incentive policy to achieve the same level of revenue. Additionally, our numerical experiments with real-world and synthetic datasets validate the effectiveness of our personalized incentive algorithms over fixed strategies.
Mo Liu is an assistant professor in the Department of Statistics and Operations Research at the University of North Carolina at Chapel Hill. His research focuses on data-driven decision-making and machine learning, with a particular emphasis on decision-focused learning—a methodology that designs and trains prediction models to account for decision-making in downstream optimization problems. These downstream problems include real-world applications in revenue management, such as product recommendation, assortment optimization and inventory management. Prior to joining UNC-Chapel Hill, he received his Ph.D. from the University of California, Berkeley, in 2024, and his bachelor’s degree from Tsinghua University in 2019.
