Application of Deep Learning for Fraud Detection in E-Payment System
Chapter One
OBJECTIVES OF THE STUDY
The Main Objective of the study is to appraise the application of deep learning for fraud detection in e-payment systems; The specific objectives include:
- To determine the level of fraud in the e-payment system.
- To determine the nature and significance of deep learning.
- To determine the effect of the application of deep learning on fraud detection in e-payment systems.
CHAPTER TWO
LITERATURE REVIEW
INTRODUCTION
Fraud detection in online shopping systems is the hottest topic nowadays. Fraud investigators, banking systems, and electronic payment systems such as PayPal must have an efficient and complex fraud detection system to prevent fraud activities that change rapidly. According to a CyberSource report from 2017, the present fraud loss by order channel, that is, the percentage of fraud loss in their web store was 74 percent and 49 percent in their mobile channels [1]. Based on this information, the lesson is to determine anomalies across patterns of fraud behavior that have undergone change relative to the past. A good fraud detection system should be able to identify the fraud transaction accurately and should make the detection possible in real- time transactions. Fraud detection can be divided into two groups: anomaly detection and misuse detection [2]. Anomaly detection systems bring normal transaction to be trained and use techniques to determine novel frauds. Conversely, a misuse fraud detection system uses the labeled transaction as normal or fraud transaction to be trained in the database history. So, this misuse detection system entails a system of supervised learning and anomaly detection system a system of unsupervised learning.
Electronic Fraud is increasing with the expansion of modern technology and global communication. This increase in the fraudulent transactions, resulting in substantial losses to the businesses, and therefore, fraud detection has become an important issue to be considered. Fraud detection can be seen as a problem of classification of legitimate transactions from the fraudulent transactions. Existing fraud detection techniques have been implemented by a number of methods such as data mining, statistics, and artificial intelligence. In general, fraud detection is a prediction problem and its objective is to maximize correct prediction and maintain incorrect predictions at an acceptable level of cost. Recent studies have shown that data mining using Artificial Intelligence (AI) techniques achieved better performance than traditional statistical methods for building prediction models [2, 12]. AI techniques, particularly rule-based expert systems, case-based reasoning systems and machine learning (ML) techniques such as neural networks have been used to support such analysis and classification problems. The major difference between traditional statistical methods and machine learning methods is that: in statistical methods usually researchers impose structures to different models, and construct the model by estimating parameters to fit the data or observation, while machine learning techniques allow learning the particular structure of the model from the data [12]. As a result, the structures of the models used in statistical methods are relatively simple, easy to interpret and tend to under-fit the data while models obtained in machine learning methods are usually very complicated, hard to explain and tend to overfit the data. Under-fit and over-fit of the data is in fact the trade-off between the explanatory power and parsimony of a model, where explanatory power leads to high prediction accuracy and parsimony usually assures generalizability and interpretability of the model.
CHAPTER THREE
METHODOLOGY
This section covers the methods used to address the objectives of the study. The section discusses the research design, research population and sampling technique, the instrument for data collection, the method of data analysis and the analytical software used for the study.
Research Design
In this study, a survey research design is adopted. Survey is chosen based on the objectives of the study. Survey is defined according to Nworgu (2005) a survey studies the sampling of individual units from an already known population and its associated survey data collection techniques, such as questionnaire construction and methods for improving the number and accuracy of responses to survey.
Population of the Study
The population of this study comprises all e-payment experts in Uyo, Akwa Ibom state.
CHAPTER FOUR
PRESENTATION AND ANALYSIS OF RESULTS
This section presents the results of the field study; it shows the descriptive information of the respondents, the results of each of the research questions and the test of hypotheses.
CHAPTER FIVE
SUMMARY, CONCLUSION AND RECOMMENDATIONS
Summary
This study focused on the application of Deep learning for fraud detection in e-payment system. The study was set to address three major research objectives. The objectives which include:
- To determine the level of fraud in e-payment system.
- To determine the nature and significance of deep learning.
- To determine the effect of the application of deep learning on fraud detection in e-payment system.
Based on the above stated objectives and the study carried out, the following findings were made:
- that there is a high level of fraud in the e-payment system.
- that deep learning is very significant.
- that the effect of the application of deep learning on fraud detection in e-payment system include that it helps in easy detection of fraud in the e-payment system; it helps the AI system; it helps in beefing up security in the e-payment system; it helps in the acceptability of the e-payment system and it makes the payment system faster.
Conclusion
The main purpose of this study is to assess the application of Deep learning for fraud detection in e-payment system. The study was set to address three research objectives. Three research questions guided the study.
In this study, a survey research design was adopted, the population comprises all e-payment system experts in Uyo, Akwa Ibom state, a simple random sampling technique was used to select 100 respondents for the study and a questionnaire was the instrument for data collection. Relevant literatures were reviewed which guided the objectives and methodology of this study. As result of the field study and analysis of results, the following findings were made:
- that there is a high level of fraud in the e-payment system.
- that deep learning is very significant.
- that the effect of the application of deep learning on fraud detection in e-payment system include that it helps in easy detection of fraud in the e-payment system; it helps the AI system; it helps in beefing up security in the e-payment system; it helps in the acceptability of the e-payment system and it makes the payment system faster.
Recommendations
Based on the findings of this study, the following recommendations are made:
- Efforts should be made to enlighten the masses on the processes and working of deep learning.
- Government at all levels should ensure the adoption of deep learning in all e-payment systems.
- There should be proper orientation of the stakeholders on the need to apply deep learning for fraud detection in e-payment system.
REFERENCES
- Andreas L. Prodromidis and Salvatore J. Stolfo; “Agent-Based Distributed Learning Applied to Fraud Detection”; Department of Computer Science- Columbia University; 2000.
- Carolyn Mair, Gada Kadoda, Martin Lefley, and others; “An investigation of machine learning based prediction systems”; The journal of System Software 53; 2000; pp. 23-29.
- Clifton Phua, Damminda Alahakoon, and Vincent Lee; “Minority Report in Fraud Detection: Classification of Skewed Data”; Sigkdd Explorations, Vol. 6, Issue 1, p.p. 50-51.
- Dean W. Abbott, I. philip Matkovsky, John F. Elder; “An Evaluation of High-end Data Mining Tools for Fraud Detection; Elder Research – San Diego. CA 9212; oct. 1998.
- Jesus Mena; “Investigative Data mining for Security and Criminal Detection”; B. H. pub. Company; 2003
- Kevin J. Leonard; “The development of a rule based expert system model for fraud alert consumer credit”; European journal of operational research, vol. 80, p.p. 350-356; 1995.
- Maes S. Tuyls K. Vanschoenwinkel B. and Manderick B.; “Credit Card Fraud Detection Using Bayesian and Neural Networks”; Vrije University Brussel – Belgium; 2002.
