ABSTRACT

CHAPTER ONE

INTRODUCTION

1. 1. Background of the Study

Credit card fraud increases as ecommerce becomes more prevalent, global credit card fraud losses increased from $7.6 billion in 2010 to $21.81 billion in 2015. By 2020, global credit card fraud losses are expected to reach $31.67 billion Robertson (2016).

However, current fraud detection techniques are far from accurate, and can result in significant financial losses to merchants and card issuers. With the advancement of fraud detection technology, fraudsters are constantly improving the concealment of fraud and avoiding being discovered. Credit card fraud detection methods are divided into two categories: supervised and unsupervised. In the supervised fraud detection method, models are estimated based on samples of fraud and legitimate transactions, and new transactions are classified as fraudulent or legal. In unsupervised fraud detection, outliers or unusual transactions are identified as potential fraudulent transaction cases. Both methods of fraud detection can predict the likelihood of fraud in any given transaction (Jha et al., 2012).

The internet is the great invention of the modern times. The users of the internet are increasing day by day. The business organizations or companies also started their business through this online medium. These business companies are providing the facility of online buying to their customers. Customers can buy the required products through the website or ecommerce stores of these companies. Most customers use credit card for buying things online. In this way, some of the customers can be the thief who has stolen the card of a person to make the online transactions. This is considered as the credit card fraud that must be detected. This fraud can also be in the form of any purchase by using the credit card in an unauthorized way. The cases of this kind of fraud are increasing. It is necessary to solve this challenging issue. Artificial intelligence is saving the time of humans in different fields. Especially machine learning, which is the branch of artificial intelligence is very helpful in performing the complex and difficult tasks. Many researchers used this sub field of artificial intelligence as a solution to various problems. It is necessary to handle the credit card fraud problem through the machine learning because this cannot be done by a human being in a proper way (Khan et al., 2014).

Online customers are increasing day by day. The customers now want to purchase the goods by sitting at their homes because of different reasons. For example, purchasing goods online saves the time of the customers. The increasing number of online customers makes credit card fraud, a more challenging and important problem. Electronic payment has several issues but the major issue is the credit card fraud (Vadlamudi, 2015).

1. 2. Statement of the Problem

With the growth of e-commerce websites, people and financial companies rely on online services to carry out their transactions that have led to an exponential increase in the credit card frauds. Fraudulent credit card transactions lead to a loss of huge amount of money. The design of an effective fraud detection system is necessary in order to reduce the losses incurred by the customers and financial companies using machine learning.

1. 3. Aim and Objectives of the Study

The aim of this research work is to design and implement a credit card fraud detection system using machine learning.

The objectives include the following;

1. To review related literatures pointing to credit card fraud detection system.
2. Allow the quick and efficient detection of credit card fraud.
3. Reduce the time delay in blocking a card once a fraudulent activity is detected.
4. Build a framework for further research in credit card detection systems.

1.4     Significance of the Study

The project credit card fraud detection system will aid in saving users who make use of their Credit cards in online platforms in a more efficient way, which in turn will reduce the amount of money being lost in this regard.

1.5     Scope of the Study

This research work covers the design and implementation of credit card fraud detection system that will aid in the detection of fraudulent activities using credit cards in online platforms.

1.6     Limitation of the Study

The researcher faced some limitations during the course of this research. Some of this limitations/constraint includes;

i.        Time constraint: Time factor were also the major factors as the timeframe to submit the project was too short for an extensive research.

ii.       Financial constraint:  Lack of adequate finance to fund the researcher as to visit many places was another major setback.

0. 7. Definition of Terms
1.  Algorithm: is a finite sequence of well-defined, computer-implementable instructions, typically to solve a class of specific problems or to perform a computation.
2. Automation: describes a wide range of technologies that reduce human intervention in processes. Human intervention is reduced by predetermining decision criteria, subprocess relationships, and related actions
3. Credit Card: A credit card is a payment card issued to users to enable the cardholder to pay a merchant for goods and services based on the cardholder's accrued debt.
4. Electronic: This is a device having or operating with components such as microchips and transistors that control and directs electronic currents.
5. Fraud: A wrongful or criminal deception intended to result in financial or personal gain.
6. Machine Learning: Machine learning is the study of computer algorithms that can improve automatically through experience and by the use of data. It is seen as a part of artificial intelligence
7. Management: Management is a process of planning, decision making, organizing, leading, motivation and controlling the human resources, financial, physical, and information resources of an organization to reach its goals in an efficient and effective manner.
8. System: is a group of interacting or interrelated elements that act according to a set of rules to form a unified whole. A system, surrounded and influenced by its environment, is described by its boundaries, structure and purpose and expressed in its functioning.
9. Technology: This is the application of scientific knowledge for practical purposes, especially in industry.
10. Unified Modeling Language: The Unified Modeling Language is a general-purpose, developmental, modeling language in the field of software engineering that is intended to provide a standard way to visualize the design of a system.
11. Upload: This is simply a process of transferring data or files from peripheral or subordinate system to a larger or more central one, especially from a personal computer to an internet server.