Competition-Based Dynamic Pricing in Online Retailing: A Methodology Validated with Field Experiments

Abstract

A retailer following a competition-based dynamic pricing strategy tracks competitors' price changes and then must answer the following questions: (1) Should the retailer respond? (2) If so, respond to whom?(3) How much of a response? (4) And on which products? The answers require unbiased measures of price elasticity as well as accurate knowledge of competitor significance and the extent to which consumers compare prices across retailers. To quantify these factors empirically, there are two key challenges: first, the endogeneity associated with almost any type of observational data, where prices are correlated with demand shocks observable to pricing managers but not to researchers; and second, the absence of competitor sales information, which prevents efficient estimation of a full consumer-choice model. We address the first issue by conducting a field experiment with randomized prices. We resolve the second issue by proposing an identification strategy that exploits the retailer's own and competitors' stock-outs as a valid source of variation to the consumer choice set. We estimate an empirical model capturing consumer choices among substitutable products from multiple retailers. Based on the estimates, we propose a best-response pricing strategy that takes into account consumer choice behavior, competitors' actions, and supply parameters (procurement costs, margin target, and manufacturer price restrictions). We test our algorithm through a carefully controlled live experiment that lasts for five weeks. The experiment documents an 11 percent revenue increase, while maintaining margin above a retailer specified target.

Mapping the Ethicality of Algorithmic Pricing: A Review of Dynamic and Personalized Pricing

“…Given that pricing algorithms haven been around for quite some time, growing academic literature is not the only reason for their diffusion (Ajorlou et al 2018;Chen et al 2016a;Peura and Bunn 2015;Spann et al 2015). Algorithms depend on data and their effectiveness grows in tandem with an increase in data input (Fisher et al 2018;Miklós-Thal and Tucker 2019).…”

“…Algorithmic pricing has spread into multiple industries and is now considered a highly advanced business approach and key driver of business success in terms of increased profits (Cosguner et al 2018;Fisher et al 2018;Spann et al 2015). Electricity and gasoline markets (Balmaceda and Soruco 2008;Faruqui and Sergici 2010), online retailing (Fisher et al 2018), and even the sports and entertainment Table 1 Data collection and selection criteria Search terms "dynamic pricing"; "personalized pricing"; "personalised pricing"; "customized pricing"; "customised pricing"; "algorithmic pricing"; "pricing algorithm" Letters to the editor, commentaries, tutorials, conference abstracts, opinions, viewpoints, as well as studies without direct relation to dynamic/personalized pricing were excluded industry have implemented algorithmic pricing approaches (Bouchet et al 2016;Chen and Chen 2015). Moreover, when it comes to the pricing of professional graduate programs, financial, or insurance products, and services, or information goods, individual prices are already a common practice (Feldman et al 2015;Waldfogel 2015).…”

“…Pricing algorithms process input data about markets and actors, accounting for numerous factors such as competitors' prices, consumer demand, or personal behavior and characteristics (such as gender, age, educational background etc.) to determine the output price in relation to the highest (i.e., profit-maximizing prices) achievable revenue (Cohen 2018;Fisher et al 2018;Keskin and Zeevi 2014;Zhang 2011). Different use case scenarios require different types of pricing algorithms, which can be broadly categorized as adaptive algorithms (first generation), and learning algorithms (second generation) (Calvano et al 2019).…”

Sustainable Supply Chains in the Age of AI and Digitization: Research Challenges and Opportunities

“…Pricing decisions can now be made in near real time using a variety of new data sources-competitor pricing, demand and supply economics, and customer characteristics (Fisher et al 2018;Simchi-Levi 2017). Uber, for example, uses "surge" pricing based on demand characteristics.…”

Dynamic pricing and learning with competition: insights from the dynamic pricing challenge at the 2017 INFORMS RM & pricing conference

“…Perakis and Sood (2006) (see also ) take a robust-optimization approach to the dynamic oligopoly pricing problem, and study Nash equilibrium policies. Fisher et al (2017) conduct a field experiment with randomized prices to estimate a consumer-choice model that does not require competitor sales observations, design a bestresponse pricing strategy, and test it with a field experiment for a leading Chinese online retailer.…”