A product-centric data mining algorithm for targeted promotions

Raymond Moodley, Francisco Chiclana, Fabio Caraffini, Jenny Carter

Research output: Contribution to journalArticle

Abstract

Targeted promotions in retail are becoming increasingly popular, particularly in UK grocery retail sector, where competition is stiff and consumers remain price sensitive. Given this, a targeted promotion algorithm is proposed to enhance the effectiveness of promotions by retailers. The algorithm leverages a mathematical model for optimising items to target and fuzzy c-means clustering for finding the best customers to target. Tests using simulations with real life consumer scanner panel data from the UK grocery retailer sector show that the algorithm performs well in finding the best items and customers to target whilst eliminating “false positives” (targeting customers who do not buy a product) and reducing “false negatives” (not targeting customers who could buy a product). The algorithm also shows better performance when compared to a similar published framework, particularly in handling “false positives” and “false negatives”. The paper concludes by discussing managerial and research implications, and highlights applications of the model to other fields.

Original languageEnglish
Article number101940
JournalJournal of Retailing and Consumer Services
Early online date3 Oct 2019
DOIs
Publication statusE-pub ahead of print - 3 Oct 2019

Fingerprint

Data mining
Mathematical models
Grocery
Targeting
Retailers

Cite this

@article{988d27d3d622477e9494b55d4244229f,
title = "A product-centric data mining algorithm for targeted promotions",
abstract = "Targeted promotions in retail are becoming increasingly popular, particularly in UK grocery retail sector, where competition is stiff and consumers remain price sensitive. Given this, a targeted promotion algorithm is proposed to enhance the effectiveness of promotions by retailers. The algorithm leverages a mathematical model for optimising items to target and fuzzy c-means clustering for finding the best customers to target. Tests using simulations with real life consumer scanner panel data from the UK grocery retailer sector show that the algorithm performs well in finding the best items and customers to target whilst eliminating “false positives” (targeting customers who do not buy a product) and reducing “false negatives” (not targeting customers who could buy a product). The algorithm also shows better performance when compared to a similar published framework, particularly in handling “false positives” and “false negatives”. The paper concludes by discussing managerial and research implications, and highlights applications of the model to other fields.",
keywords = "Targeted promotions, Algorithm, Association rule mining, Targeted marketing, Clustering",
author = "Raymond Moodley and Francisco Chiclana and Fabio Caraffini and Jenny Carter",
year = "2019",
month = "10",
day = "3",
doi = "10.1016/j.jretconser.2019.101940",
language = "English",
journal = "Journal of Retailing and Consumer Services",
issn = "0969-6989",
publisher = "Elsevier Limited",

}

A product-centric data mining algorithm for targeted promotions. / Moodley, Raymond; Chiclana, Francisco; Caraffini, Fabio; Carter, Jenny.

In: Journal of Retailing and Consumer Services, 03.10.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A product-centric data mining algorithm for targeted promotions

AU - Moodley, Raymond

AU - Chiclana, Francisco

AU - Caraffini, Fabio

AU - Carter, Jenny

PY - 2019/10/3

Y1 - 2019/10/3

N2 - Targeted promotions in retail are becoming increasingly popular, particularly in UK grocery retail sector, where competition is stiff and consumers remain price sensitive. Given this, a targeted promotion algorithm is proposed to enhance the effectiveness of promotions by retailers. The algorithm leverages a mathematical model for optimising items to target and fuzzy c-means clustering for finding the best customers to target. Tests using simulations with real life consumer scanner panel data from the UK grocery retailer sector show that the algorithm performs well in finding the best items and customers to target whilst eliminating “false positives” (targeting customers who do not buy a product) and reducing “false negatives” (not targeting customers who could buy a product). The algorithm also shows better performance when compared to a similar published framework, particularly in handling “false positives” and “false negatives”. The paper concludes by discussing managerial and research implications, and highlights applications of the model to other fields.

AB - Targeted promotions in retail are becoming increasingly popular, particularly in UK grocery retail sector, where competition is stiff and consumers remain price sensitive. Given this, a targeted promotion algorithm is proposed to enhance the effectiveness of promotions by retailers. The algorithm leverages a mathematical model for optimising items to target and fuzzy c-means clustering for finding the best customers to target. Tests using simulations with real life consumer scanner panel data from the UK grocery retailer sector show that the algorithm performs well in finding the best items and customers to target whilst eliminating “false positives” (targeting customers who do not buy a product) and reducing “false negatives” (not targeting customers who could buy a product). The algorithm also shows better performance when compared to a similar published framework, particularly in handling “false positives” and “false negatives”. The paper concludes by discussing managerial and research implications, and highlights applications of the model to other fields.

KW - Targeted promotions

KW - Algorithm

KW - Association rule mining

KW - Targeted marketing

KW - Clustering

UR - http://www.scopus.com/inward/record.url?scp=85072768315&partnerID=8YFLogxK

U2 - 10.1016/j.jretconser.2019.101940

DO - 10.1016/j.jretconser.2019.101940

M3 - Article

JO - Journal of Retailing and Consumer Services

JF - Journal of Retailing and Consumer Services

SN - 0969-6989

M1 - 101940

ER -