Saved in:
Bibliographic Details
Main Authors: Baek, Jackie, Ma, Will, Mitrofanov, Dmitry
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.23781
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909978056458240
author Baek, Jackie
Ma, Will
Mitrofanov, Dmitry
author_facet Baek, Jackie
Ma, Will
Mitrofanov, Dmitry
contents Partnering with a large online retailer, we consider the problem of sending daily personalized promotions to a userbase of over 20 million customers. We propose an efficient policy for determining, every day, the promotion that each customer should receive (10%, 12%, 15%, 17%, or 20% off), while respecting global allocation constraints. This policy was successfully deployed to see a 4.5% revenue increase during an A/B test, by better targeting promotion-sensitive customers and also learning intertemporal patterns across customers. We also consider theoretically modeling the intertemporal state of the customer. The data suggests a simple new combinatorial model of pricing with reference effects, where the customer remembers the best promotion they saw over the past $\ell$ days as the "reference value", and is more likely to purchase if this value is poor. We tightly characterize the structure of optimal policies for maximizing long-run average revenue under this model -- they cycle between offering poor promotion values $\ell$ times and offering good values once.
format Preprint
id arxiv_https___arxiv_org_abs_2512_23781
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Personalized Promotions in Practice: Dynamic Allocation and Reference Effects
Baek, Jackie
Ma, Will
Mitrofanov, Dmitry
Computer Science and Game Theory
Partnering with a large online retailer, we consider the problem of sending daily personalized promotions to a userbase of over 20 million customers. We propose an efficient policy for determining, every day, the promotion that each customer should receive (10%, 12%, 15%, 17%, or 20% off), while respecting global allocation constraints. This policy was successfully deployed to see a 4.5% revenue increase during an A/B test, by better targeting promotion-sensitive customers and also learning intertemporal patterns across customers. We also consider theoretically modeling the intertemporal state of the customer. The data suggests a simple new combinatorial model of pricing with reference effects, where the customer remembers the best promotion they saw over the past $\ell$ days as the "reference value", and is more likely to purchase if this value is poor. We tightly characterize the structure of optimal policies for maximizing long-run average revenue under this model -- they cycle between offering poor promotion values $\ell$ times and offering good values once.
title Personalized Promotions in Practice: Dynamic Allocation and Reference Effects
topic Computer Science and Game Theory
url https://arxiv.org/abs/2512.23781