We consider an electric utility company that serves retail electricity customers over a discrete-time horizon. In each period, the company observes the customers' consumption as well as high-dimensional features on customer characteristics and exogenous factors. A distinctive element of our work is that these features exhibit three types of heterogeneity—over time, customers, or both. Based on the consumption and feature observations, the company can dynamically adjust the retail electricity price at the customer level. The consumption depends on the features: there is an underlying structure of clusters in the feature space, and the relationship between consumption and features is different in each cluster. Initially, the company knows neither the underlying cluster structure nor the corresponding consumption models. We design a data-driven policy of joint spectral clustering and feature-based pricing and show that our policy achieves near-optimal performance, i.e., its average regret converges to zero at the fastest achievable rate. This work is the first to theoretically analyze joint clustering and feature-based pricing with different types of feature heterogeneity. Our case study based on real-life smart meter data from Texas illustrates that our policy increases company profits by 146% over a three-month period relative to the company policy, and is robust to various forms of model misspecification. (This is joint work with Yuexing Li and Nur Sunar.)
Bora Keskin is an Associate Professor in the Operations Management area at the Fuqua School of Business at Duke University. Bora received his Ph.D. from the Graduate School of Business at Stanford University in 2012. Before joining the faculty at Duke University in 2015, he worked at McKinsey & Company as a consultant in banking and telecommunications industries, and at the University of Chicago as an Assistant Professor of Operations Management.
Bora's main research explores data-driven decision making in complex business problems. In particular, he is interested in stochastic models and their application to revenue management, dynamic pricing, statistical learning, machine learning, and product differentiation. In 2019, Bora was awarded the Lanchester Prize for the development of a novel paradigm for the modeling and analysis of online dynamic optimization problems that are subject to temporal uncertainty.
Bora has taught Value Chain Innovation as well as Supply Chain Management for the Daytime and Executive MBA programs, and Revenue Management and Pricing for the PhD program at Fuqua. Outside Duke, Bora serves an Associate Editor for Management Science and Operations Research. He also served as an Associate Editor for the Management Science Special Issue on Data-Driven Prescriptive Analytics, as a Board Member for the INFORMS Revenue Management and Pricing (RMP) Section, and as a Cluster Chair for the RMP and MSOM-Service tracks at INFORMS Annual Meetings.