Online Pricing with Offline Data: Phase Transition and Inverse Square Law

TL;DR

This paper explores how pre-existing offline data influences online dynamic pricing, revealing phase transitions and an inverse-square law in regret bounds, and proposes an optimal learning algorithm.

Contribution

It characterizes the joint effects of offline data size, location, and dispersion on regret, introducing phase transition phenomena and the inverse-square law in this context.

Findings

Optimal regret depends on offline data size, location, and dispersion.

Phase transitions occur in regret rates based on offline data characteristics.

An algorithm achieving near-optimal regret is proposed.

Abstract

This paper investigates the impact of pre-existing offline data on online learning, in the context of dynamic pricing. We study a single-product dynamic pricing problem over a selling horizon of $T$ periods. The demand in each period is determined by the price of the product according to a linear demand model with unknown parameters. We assume that before the start of the selling horizon, the seller already has some pre-existing offline data. The offline data set contains $n$ samples, each of which is an input-output pair consisting of a historical price and an associated demand observation. The seller wants to utilize both the pre-existing offline data and the sequential online data to minimize the regret of the online learning process. We characterize the joint effect of the size, location and dispersion of the offline data on the optimal regret of the online learning process. Specifically, the size, location and dispersion of the offline data are measured by the number of historical samples $n$, the distance between the average historical price and the optimal price $\delta$, and the standard deviation of the historical prices $\sigma$, respectively. We show that the optimal regret is $\widetilde \Theta\left(\sqrt{T}\wedge \frac{T}{(n\wedge T)\delta^2+n\sigma^2}\right)$, and design a learning algorithm based on the "optimism in the face of uncertainty" principle, whose regret is optimal up to a logarithmic factor. Our results reveal surprising transformations of the optimal regret rate with respect to the size of the offline data, which we refer to as phase transitions. In addition, our results demonstrate that the location and dispersion of the offline data also have an intrinsic effect on the optimal regret, and we quantify this effect via the inverse-square law.