Application of Uninorms to Market Basket Analysis

Raymond Moodley, Francisco Chiclana, Fabio Caraffini, Jenny Carter

Research output: Contribution to journalArticle

Abstract

The ability for grocery retailers to have a single view of customers across all their grocery purchases remains elusive and has become increasingly important in recent years (especially in the United Kingdom) where competition has intensified, shopping habits and demographics have changed and price sensitivity has increased following the 2008 recession. Numerous studies have been conducted on understanding independent items that are frequently bought together (association rule mining/frequent itemsets) with several measures proposed to aggregate item support and rule confidence with varying levels of accuracy as these measures are highly context dependent. Uninorms were used as an alternative measure to aggregate support and confidence in analysing market basket data using the UK grocery retail sector as a case study. Experiments were conducted on consumer panel data with the aim of comparing the uninorm against three other popular measures (Jaccard, Cosine and Conviction). It was found that the uninorm outperformed other models on its adherence to the fundamental monotonicity property of support in market basket analysis (MBA). Future work will include the extension of this analysis to provide a generalised model for market basket analysis.

LanguageEnglish
Pages39-49
Number of pages11
JournalInternational Journal of Intelligent Systems
Volume34
Issue number1
Early online date18 Oct 2018
DOIs
Publication statusPublished - Jan 2019

Fingerprint

Uninorm
Association rules
Confidence
Frequent Itemsets
Association Rule Mining
Panel Data
Monotonicity
Sector
Customers
Experiments
Market
Dependent
Alternatives
Model
Experiment

Cite this

Moodley, Raymond ; Chiclana, Francisco ; Caraffini, Fabio ; Carter, Jenny. / Application of Uninorms to Market Basket Analysis. In: International Journal of Intelligent Systems. 2019 ; Vol. 34, No. 1. pp. 39-49.
@article{f53ea3d65be14999854794acfd4cbecd,
title = "Application of Uninorms to Market Basket Analysis",
abstract = "The ability for grocery retailers to have a single view of customers across all their grocery purchases remains elusive and has become increasingly important in recent years (especially in the United Kingdom) where competition has intensified, shopping habits and demographics have changed and price sensitivity has increased following the 2008 recession. Numerous studies have been conducted on understanding independent items that are frequently bought together (association rule mining/frequent itemsets) with several measures proposed to aggregate item support and rule confidence with varying levels of accuracy as these measures are highly context dependent. Uninorms were used as an alternative measure to aggregate support and confidence in analysing market basket data using the UK grocery retail sector as a case study. Experiments were conducted on consumer panel data with the aim of comparing the uninorm against three other popular measures (Jaccard, Cosine and Conviction). It was found that the uninorm outperformed other models on its adherence to the fundamental monotonicity property of support in market basket analysis (MBA). Future work will include the extension of this analysis to provide a generalised model for market basket analysis.",
keywords = "Uninorms, Frequent itemset mining, Market basket analysis, Aggregate measures, Support, Confidence",
author = "Raymond Moodley and Francisco Chiclana and Fabio Caraffini and Jenny Carter",
year = "2019",
month = "1",
doi = "10.1002/int.22039",
language = "English",
volume = "34",
pages = "39--49",
journal = "International Journal of Intelligent Systems",
issn = "0884-8173",
publisher = "John Wiley and Sons Ltd",
number = "1",

}

Application of Uninorms to Market Basket Analysis. / Moodley, Raymond; Chiclana, Francisco; Caraffini, Fabio; Carter, Jenny.

In: International Journal of Intelligent Systems, Vol. 34, No. 1, 01.2019, p. 39-49.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Application of Uninorms to Market Basket Analysis

AU - Moodley, Raymond

AU - Chiclana, Francisco

AU - Caraffini, Fabio

AU - Carter, Jenny

PY - 2019/1

Y1 - 2019/1

N2 - The ability for grocery retailers to have a single view of customers across all their grocery purchases remains elusive and has become increasingly important in recent years (especially in the United Kingdom) where competition has intensified, shopping habits and demographics have changed and price sensitivity has increased following the 2008 recession. Numerous studies have been conducted on understanding independent items that are frequently bought together (association rule mining/frequent itemsets) with several measures proposed to aggregate item support and rule confidence with varying levels of accuracy as these measures are highly context dependent. Uninorms were used as an alternative measure to aggregate support and confidence in analysing market basket data using the UK grocery retail sector as a case study. Experiments were conducted on consumer panel data with the aim of comparing the uninorm against three other popular measures (Jaccard, Cosine and Conviction). It was found that the uninorm outperformed other models on its adherence to the fundamental monotonicity property of support in market basket analysis (MBA). Future work will include the extension of this analysis to provide a generalised model for market basket analysis.

AB - The ability for grocery retailers to have a single view of customers across all their grocery purchases remains elusive and has become increasingly important in recent years (especially in the United Kingdom) where competition has intensified, shopping habits and demographics have changed and price sensitivity has increased following the 2008 recession. Numerous studies have been conducted on understanding independent items that are frequently bought together (association rule mining/frequent itemsets) with several measures proposed to aggregate item support and rule confidence with varying levels of accuracy as these measures are highly context dependent. Uninorms were used as an alternative measure to aggregate support and confidence in analysing market basket data using the UK grocery retail sector as a case study. Experiments were conducted on consumer panel data with the aim of comparing the uninorm against three other popular measures (Jaccard, Cosine and Conviction). It was found that the uninorm outperformed other models on its adherence to the fundamental monotonicity property of support in market basket analysis (MBA). Future work will include the extension of this analysis to provide a generalised model for market basket analysis.

KW - Uninorms

KW - Frequent itemset mining

KW - Market basket analysis

KW - Aggregate measures

KW - Support

KW - Confidence

UR - http://www.scopus.com/inward/record.url?scp=85055271473&partnerID=8YFLogxK

U2 - 10.1002/int.22039

DO - 10.1002/int.22039

M3 - Article

VL - 34

SP - 39

EP - 49

JO - International Journal of Intelligent Systems

T2 - International Journal of Intelligent Systems

JF - International Journal of Intelligent Systems

SN - 0884-8173

IS - 1

ER -