Practices, controls and capabilities: a thematic analysis of Big Data in e-retail fraud management

Purpose Prior Big Data and fraud research emphasises technical detection or generic analytics, offering limited empirical insight into how Big Data is operationalised as practices and controls in e-retail fraud prevention. This study examines how e-retail firms translate analytics capabilities into fraud prevention practices and controls. Design/methodology/approach The study draws on 32 semi-structured interviews across 18 e-retail organisations and applies abductive thematic analysis to examine how Big Data resources are translated into fraud prevention practices and controls. Findings Findings reveal that Big Data enables fraud prevention not merely through detection technologies, but through two empirically derived transformation practices: (1) Localised Exploitation, which translates complex analytics into simplified, role-specific reporting routines; and (2) Personalised Care Practice, which develops and cross-references business-unit-specific fraud risk profiles to identify emerging threats. These practices generate data-driven fraud controls by strengthening technical safeguards, refining formal policies, streamlining fraud reporting and reinforcing behavioural controls through analytics-informed training. Their effectiveness, however, is constrained by regulatory complexity, limited inter-organisational knowledge sharing and reliance on outsourced analytics providers. Originality/value This study makes three key empirical contributions. First, it moves beyond conceptual Big Data research by showing how analytics capabilities are enacted as organisational practices in e-retail fraud prevention. Second, it advances theory by integrating the Practice-Based View and the Balanced Control Paradigm into an empirically grounded Integrated Big Data-Enabled Fraud Prevention (IBDEFP) model. Third, it provides actionable insights into designing analytics, controls and human engagement to strengthen adaptive fraud management in volatile digital environments.

Authors

Institutions

Publication Details

Journal
Journal of Enterprise Information Management
Published
2026-04-15
DOI
https://doi.org/10.1108/jeim-06-2025-0441
Primary Topic
Imbalanced Data Classification Techniques
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Practices, controls and capabilities: a thematic analysis of Big Data in e-retail fraud management

Alexeis García-Pérez, Maureen Meadows, Justin Okoli, Chiwuokem Nwoko
Journal of Enterprise Information Management
Imbalanced Data Classification Techniques
article

Practices, controls and capabilities: a thematic analysis of Big Data in e-retail fraud management

Alexeis García-Pérez, Maureen Meadows, Justin Okoli, Chiwuokem Nwoko
article en

Abstract

Purpose Prior Big Data and fraud research emphasises technical detection or generic analytics, offering limited empirical insight into how Big Data is operationalised as practices and controls in e-retail fraud prevention. This study examines how e-retail firms translate analytics capabilities into fraud prevention practices and controls. Design/methodology/approach The study draws on 32 semi-structured interviews across 18 e-retail organisations and applies abductive thematic analysis to examine how Big Data resources are translated into fraud prevention practices and controls. Findings Findings reveal that Big Data enables fraud prevention not merely through detection technologies, but through two empirically derived transformation practices: (1) Localised Exploitation, which translates complex analytics into simplified, role-specific reporting routines; and (2) Personalised Care Practice, which develops and cross-references business-unit-specific fraud risk profiles to identify emerging threats. These practices generate data-driven fraud controls by strengthening technical safeguards, refining formal policies, streamlining fraud reporting and reinforcing behavioural controls through analytics-informed training. Their effectiveness, however, is constrained by regulatory complexity, limited inter-organisational knowledge sharing and reliance on outsourced analytics providers. Originality/value This study makes three key empirical contributions. First, it moves beyond conceptual Big Data research by showing how analytics capabilities are enacted as organisational practices in e-retail fraud prevention. Second, it advances theory by integrating the Practice-Based View and the Balanced Control Paradigm into an empirically grounded Integrated Big Data-Enabled Fraud Prevention (IBDEFP) model. Third, it provides actionable insights into designing analytics, controls and human engagement to strengthen adaptive fraud management in volatile digital environments.

Journal of Enterprise Information Management
Aston University (GB), University of Derby (GB), Coventry University (GB), University of Plymouth (GB)
Peace, Justice and strong institutions
Openalex Percentile: Top 21%
Imbalanced Data Classification Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.