Durrmeyer, Isis, Fournel, Jean-François and Samano, Mario (2026) Personalized Pricing and the Value of Past Purchase Histories: An Empirical Perspective. TSE Working Paper, n. 26-1779

[thumbnail of wp_tse_1779.pdf]
Preview
Text
Download (4MB) | Preview

Abstract

Grocery loyalty programs record purchase histories that retailers do not use to personalize prices. We measure how much they forgo with a structural model of demand and pricing in which a Bayesian seller learns preferences from past purchases and personalizes prices. Profits rise by 7.1% with one-year histories, capturing two thirds of the gains under perfect knowledge of preferences. Most consumers (84.1%) gain, but the losses of the minority outweigh these gains, and aggregate consumer surplus falls. An optimal loyalty program charges a membership fee, yet most consumers enroll, because opting out signals price insensitivity.

Item Type: Monograph (Working Paper)
Language: English
Date: October 2026
Uncontrolled Keywords: personalized pricing, behavior-based price discrimination, purchase histories, Bayesian learning, loyalty programs, value of information
JEL Classification: D12 - Consumer Economics - Empirical Analysis
D42 - Monopoly
D83 - Search; Learning; Information and Knowledge; Communication; Belief
L11 - Production, Pricing, and Market Structure; Size Distribution of Firms
L81 - Retail and Wholesale Trade; Warehousing; e-Commerce
Subjects: B- ECONOMIE ET FINANCE
Divisions: TSE-R (Toulouse)
Site: UT1
Date Deposited: 21 Oct 2026 10:17
Last Modified: 21 Oct 2026 10:17
OAI Identifier: oai:tse-fr.eu:132271
URI: https://publications.ut-capitole.fr/id/eprint/54108
View Item

Downloads

Downloads per month over past year