Electronic fraud is a problem that has become a concern for businesses of all sizes. Electronic fraud increases the loss margin as criminals go beyond brick-and-mortar enterprises to target firms with an online presence and e-payment methods. The purpose of this research is to propose a framework which decision-makers can use to anticipate threats, provide preventive measures and calculate percentage gain in income upon the implementation of the preventive measures. This proposed framework will assist in safeguarding businesses and consumers from electronic fraud on selected e-payment channels. Similarly, the framework will help minimize e-payment fraud and increase customer adoption of e-payments. The data used was obtained from the Central Bank of Nigeria. The framework’s output offers decision makers in banks and financial technology firms with historical data on the amount of e-payment fraud on each of the selected channels. The framework also allows decision-makers to forecast cyber fraud on various e-payment channels. Similarly, the framework offers methods for implementing preventive measures as well as a percentage gain in income following execution.
Table of Contents
1.1 INTRODUCTION
1.1.2 E-PAYMENT FRAUD
1.2 STATEMENT OF THE PROBLEM
1.3 SIGNIFICANCE OF STUDY
1.3.1 SIGNIFICANCE OF THE STUDY: MODEL 1
1.3.2 SIGNIFICANCE OF THE STUDY: MODEL 2
1.4 RESEARCH QUESTION AND MOTIVATION
1.5 RESEARCH CONTRIBUTION
1.6 AIM AND OBJECTIVES
1.7 SCOPE OF WORK
2.1.1 THE EVOLUTION OF FRAUD
2.2 OVERVIEW OF E-PAYMENT FRAUD DETECTION AND FORECASTING
2.2.1 TYPES OF E-PAYMENT
2.2.1.1 Credit Card
2.2.1.2 Debit Card
2.2.1.3 Smart Card
2.2.1.4 E-Wallet
2.2.1.5 Online banking
2.2.1.6 Mobile-payment
2.2.1.7 Digital Wallet Payments
2.2.1.8 Direct Debits
2.3 ELECTRONIC FRAUD
2.4.1 True (classic) fraud
2.4.2 Triangulation fraud
2.4.3 Interception fraud:
2.4.4 Card validity testing fraud:
2.4.5 Chargeback fraud:
2.5 DETECTION OF CARD FRAUD
2.5.1 E-PAYMENT FRAUD DETECTION TECHNIQUES
2.5.1.1 RULE-BASED APPROACHES
2.6 REQUIREMENT FOR A FRAMEWORK THAT CAN DETECT AND FORECAST ELECTRONIC FRAUD
2.7 PREDICTIVE ANALYSIS
2.7.1 Benefits of predictive analysis for organizations
2.8 ECONOMIC INTELLIGENCE
2.9 SMALL AND MEDIUM SCALED ENTERPRISE (SME)
2.10 HACKING
2.10.1 Major business hacking types
2.10.1.1 Key logger
2.10.1.2 Denial of Service (DoS\DDoS)
2.10.1.3 Waterhole assaults
2.10.1.4 Fake WAP
2.10.1.5 Eavesdropping (Passive Attacks)
2.10.1.6 Phishing
2.10.1.7 Virus and Trojan
2.10.1.8 Click Jacking Assaults
2.10.1.9 Cookie theft
2.10.1.10 Bait and switch
3.1 INTRODUCTION
3.1.1 HISTORY OF ECONOMIC INTELLIGENCE
3.1.2 DECISION MAKING IN EI
3.1.3 BUILDING A FORECAST MODEL
3.1.4 REGRESSION ANALYSIS
3.2 FRAMEWORK FOR FORECASTING ELECTRONIC FRAUD THREATS
3.3 FRAMEWORK FOR DETECTION OF FRAUD AT POINT OF SALE ON ELECTRONIC COMMERCE SITES
3.3.1 Dataset
3.3.2 Indicators of card validity fraud
RESULT AND DISCUSSION
4.1 INTRODUCTION
4.2 QUESTIONNAIRE RESULTS
4.3 RESULT FOR FRAMEWORK FOR FORECASTING ELECTRONIC FRAUD THREATS
4.4 DISCUSSION
5.1 CONCLUSION
5.2 CONTRIBUTION TO KNOWLEDGE
5.3 RECOMMENDATION FOR FUTURE WORK
Research Objectives and Themes
The primary objective of this research is to develop comprehensive frameworks for businesses, specifically SMEs, to identify, anticipate, and mitigate electronic fraud across various payment channels. By employing predictive analytics and machine learning techniques, the research seeks to provide decision-makers with actionable insights to safeguard their operations, increase customer trust, and ultimately foster sustainable economic growth. The study addresses the challenge of e-payment security, which has become increasingly critical as digital transaction volumes rise globally and locally in Nigeria.
- Investigation and categorization of prevalent e-payment fraud techniques, including phishing, keylogging, and clickjacking.
- Development of a forecasting framework for calculating potential fraud threats and associated revenue impacts.
- Application of logistic regression models to detect fraudulent transactions at digital and physical points of sale.
- Analysis of the economic intelligence process to integrate data-driven decision support into business management.
- Formulation of effective preventive and countermeasures for SMEs to enhance transaction security.
Excerpt from the Book
2.4.2 Triangulation fraud
This sort of fraud is named after the fact that it involves a fraudster, a real shopper, and an E-commerce enterprise. A fraudster opens an online store on Amazon or eBay and offers high-demand items at exceptionally low costs. After receiving the credit card information from the people who bought, he purchases products from a real store and ships them to the customers. Triangulation fraud is a deceitful method in which criminals take advantage of the confidence and anonymity of e-commerce platforms in order to deceive unwary consumers and merchants.
To lure consumers and obtain payment information, fraudsters frequently construct fraudulent internet storefronts that pose as real retailers (Benson et al., 2021). After receiving the payment, the fraudsters begin a second transaction on a separate platform, purchasing an item from a legitimate vendor. They do, however, divert the delivery location to the unwitting buyer, thereby laundering the criminal proceeds (Carter & Morrison, 2019). Both the buyer and the legal vendor suffer financial losses as a result of this method, while the fraudsters profit from the fraudulently acquired products.
Due to the complexity of triangulation fraud, detecting it is a huge task. Researchers have developed a number of approaches for detecting and mitigating this fraudulent behaviour. By evaluating trends and abnormalities in transaction data, machine learning systems have showed potential in fraud detection (Lim et al., 2020). Social network analysis has also been used to uncover suspect buyer-seller ties and patterns of activity (Zhang et al., 2018). Furthermore, combining geolocation data with IP address analysis might give further insights into probable triangulation fraud situations (Han et al., 2021). Combining these strategies with powerful data analytics can enhance fraud detection in e-commerce systems.
Summary of Chapters
CHAPTER 1 INTRODUCTION: This chapter provides an overview of the global rise of e-payments and the accompanying security challenges, defining the background of the study and research objectives.
CHAPTER 2 LIERATURE REVIEW: This chapter examines existing scholarly work on e-payment methods, fraud detection mechanisms, and the theoretical underpinnings of economic intelligence.
CHAPTER 3 EVALUATION OF THE ECONOMIC INTELLIGENCE SYSTEM: This chapter details the architectural design and methodological approaches, including regression analysis and forecasting frameworks, used to evaluate the economic intelligence system.
CHAPTER 4 RESULT AND DISCUSSION: This chapter presents the findings from the questionnaire and the developed fraud forecasting and detection frameworks, alongside a discussion on their practical implications.
CHAPTER 5 CONCLUSION AND FUTURE WORK RECOMMENDATIONS: This chapter summarizes the contributions of the research and provides guidance for future studies in related fields.
Keywords
Decision-maker, electronic fraud, e-payment, developing countries, E-commerce, point of sale, decision making, fraud detection, logistic regression, machine learning, economic intelligence, SMEs, cybercrime, data analysis, predictive analytics.
Frequently Asked Questions
What is the primary scope of this dissertation?
This work focuses on the predictive analysis of electronic fraud within the context of small and medium-sized enterprises (SMEs) in Nigeria, proposing frameworks to forecast and detect threats across major e-payment channels.
What are the main thematic areas covered?
The study covers the evolution of various electronic fraud types, such as phishing and keylogging, methods for e-payment fraud detection, the application of predictive analytics, and the role of economic intelligence in business decision-making.
What is the core research question driving this study?
The research explores whether frameworks based on historical data and machine learning can effectively forecast cyber fraud on e-payment channels and assist in identifying fraudulent activity at points of sale to safeguard revenue.
Which scientific methodology does the author employ?
The author uses a hybrid methodology involving structural equation modeling (SEM), linear regression for forecasting fraud threats, and logistic regression for binary classification to detect fraudulent versus legitimate e-commerce transactions.
What topics are specifically addressed in the primary chapters?
The chapters treat the history and theoretical principles of economic intelligence, the technical categorization of e-payment hacking strategies, and the implementation of specific frameworks to improve security for SMEs.
Which keywords define this research?
The work is characterized by terms like electronic fraud, logistic regression, e-payment, economic intelligence, and fraud detection within the framework of developing nations.
How is triangulation fraud specifically analyzed?
The research describes triangulation fraud as a complex, three-party scheme involving a fraudster, an unwitting shopper, and a legitimate merchant, and explores its mitigation through behavioral and network data analysis.
What is the importance of the reported accuracy in this study?
The proposed framework for fraud detection at the point of sale achieved an accuracy of 97.8 percent, providing a reliable tool for decision-makers to rapidly identify and forestall fraudulent attempts.
- Arbeit zitieren
- Olubunmi Alabi (Autor:in), 2023, Predictive Analysis in Economic Intelligence. Case Studies of SMEs in Nigeria, München, GRIN Verlag, https://www.grin.com/document/1382733
