Event Details

Arnoud den Boer will present a seminar of his joint work-in-progress with Bora Keskin, Duke University, to the Management Science Department

Abstract: We consider a seller’s dynamic pricing problem with reference effects: the phenomenon that sales is not only influenced by the current price, but also by an expected, so-called reference price constructed in the minds of potential customers based on the seller’s price history. There is substantial empirical evidence that customers are loss averse: that means that the demand reduction when the selling price exceeds the reference price is larger than the demand increase when the selling price falls behind the reference price by the same amount. Consequently, the expected demand as a function of price has a time-varying “kink” and is not differentiable everywhere. The seller neither knows the underlying demand function nor observes the time-varying reference prices. In this setting, we design and analyze a policy that (i) changes the selling price very slowly to control the evolution of the reference prices, and (ii) gradually accumulates sales data to balance the trade off between learning and earning. We prove that, under a variety of reference-price updating mechanisms, our policy is asymptotically optimal; i.e., its T-period revenue loss relative to a clairvoyant who knows the demand function and the reference-price updating mechanism grows at the smallest possible rate in T. We also extend our analysis to the case of gain-seeking customers, and show that `difficulty of the learning problem’,measured by the asymptotically optimal growth rate of the regret, is parameter-dependent.

Bio: After obtaining a mathematics degree at Utrecht University (2006) and a post-master degree Mathematics for Industry at Eindhoven University of Technology (2008), Arnoud wrote his PhD thesis `Dynamic Pricing and Learning' (2013) at the CWI Centrum for Wiskunde and Computer Science,under the supervision of Bert Zwart and Rob van der Mei. After positions at Eindhoven University of Technology (postdoc), University of Amsterdam(postdoc), and University of Twente (postdoc / assistant professor), he joined the University of Amsterdam in 2016 as assistant professor in the mathematics department. He is also affiliated to the Amsterdam Business School.

Arnoud's research focuses on the interface of learning and optimization, with applications in dynamic pricing and revenue management. His PhD thesis and subsequent research has been awarded the 2015 Gijs de Leve prize for best PhD Thesis in operations research defended in the Netherlands in the period 2012-2014, a honorable mention for the Willem R. van Zwet Award for best PhD Thesis in statistics & operations research defended in the Netherlands in 2013, a finalist place for the 2015 European Doctoral Dissertation Award, an NWO Veni grant in 2014, and the INFORMS Revenue Management & Pricing Section Prize in 2016.