DEPARTMENT OF COMPUTER SCIENCE ENGINEERING

EAST WEST INSTITUTE OF POLYTECHNIC [597]

YELAHANKA NEW TOWN, BENGALURU – 560064

CREDIT CARD FRAUD

DETECTION
Under the guidance of
BY
RAMESH B.N
VIJAY KUMAR.M
[597CS20045]
HEAD OF THE
DEPARTMENT(CSE)
INTRODUCTION

CREDIT CARD FRAUD DETECTION

 It is vital that credit card companies are able to identify fraudulent credit card transactions so that
customers are not charged for items that they did not purchase.
 Such problems can be tackled with Data Science and its importance, along with Machine Learning, cannot be
overstated

2
OBJCETIVE
 This project intends to illustrate the modelling of a data set using machine learning with Credit Card Fraud
Detection.
 The Credit Card Fraud Detection Problem includes modelling past credit card transactions with the data of the
ones that turned out to be fraud.
 This model is then used to recognize whether a new transaction is fraudulent or not.

3
LITERATURE SURVEY
Prajwal Save et al. have proposed a model based on a decision tree and a combination of Luhn's and Hunt’s
algorithms.
Luhn's algorithm is used to determine whether an incoming transaction is fraudulent or not. It validates credit card
numbers via the input, which is the credit card number.

4
System Requirement Specification

Hardware Requirements

System Processor : Core i3 / i5

Hard Disk : 500 GB.

Ram : 4 GB.

Software Requirements
Operating system : Windows XP / 7

Coding Language : Python

Software : Anaconda
IDE : Jupyter Notebook

5
System Requirement Specification
Non-functional requirements

• Reliability
• Performance
• Portability
• Scalability
• Flexibility
• Security

6
Model Design

7
METHODOLOGY

This section describes about four algorithms used in this system namely

• Random Forest Algorithm

• Logistic Regression algorithm
• Naive Bayes Classifier
• Support Vector Classifier

8
Implementation

• Support Vector Machine Algorithm

• Support Vector Machine or SVM is one of the most popular Supervised Learning algorithms, which
is used for Classification as well as Regression problems.
• The goal of the SVM algorithm is to create the best line or decision boundary that can segregate n-
dimensional space into classes so that we can easily put the new data point in the correct category
in the future.
• This best decision boundary is called a hyperplane. SVM chooses the extreme points/vectors that
help in creating the hyperplane.

9
Implementation

 Random Forest Algorithm

• Random Forest is a classifier that contains a number of decision trees on various subsets of the given
dataset and takes the average to improve the predictive accuracy of that dataset.
• Random Forest is a popular machine learning algorithm that belongs to the supervised learning technique.
It can be used for both Classification and Regression problems in ML.
• The greater number of trees in the forest leads to higher accuracy and prevents the problem of overfitting.

10
Implementation
• Logistic Regression algorithm

Logistic regression is an example of supervised learning. It is used to calculate or predict the

probability of a binary (yes/no) event occurring. An example of logistic regression could be
applying machine learning to determine if a person is likely to be infected with COVID-19 or not.
Since we have two possible outcomes to this question - yes, they are infected, or no they are not
infected - this is called binary classification.

11
Implementation
• Naive Bayes classifier

• A naive Bayes classifier is an algorithm that uses Bayes' theorem to classify objects.
• Naive Bayes classifiers assume strong, or naive, independence between attributes of data points.
• Popular uses of naive Bayes classifiers include spam filters, text analysis and medical diagnosis.
• These classifiers are widely used for machine learning because they are simple to implement.

12
Snapshots

• Support Vector Machine Algorithm Snapshot 1

13
Snapshots
Logistic Regression algorithm Snapshot 2

14
Snapshots
Naive Bayes classifier algorithm Snap shot 3

15
Snapshots
• Random Forest Algorithm Snapshot 4

16
Snapshots
Random Forest Algorithm Snap 4.1 (Confusion Matrix)

17
Snap shot
Classification Accuracy Comparison of Models snap 4

18
Conclusion and future enhancement
Conclusion
• as previously mentioned algorithms from machine learning, there are many algorithms and techniques which may
perform better than these. Production of accurate classifier which perform efficiently for fraud detection application
is the main challenge we face in machine learning. Four main algorithms were implemented in this System were,
Random Forest Algorithm, Logistic Regression algorithm, Naive Bayes Classifier, Support Vector Classifier
• Our main aim for the research is to discover the algorithm which performs faster, accurate and efficiently. Random
forest surpasses all the other algorithms with an accuracy of 1.5686274509803921%.Thus I Conclude, this project
by saying Random forest Classification algorithm is best and better for handling this type of data set.

Future enhancement
• In the future, the designed system with the used machine learning classification algorithm can be used
to predict if a transaction is legit.
• The work can be extended or improved for the automation of fraud detection analysis including some
other machine learning algorithms

19
References
[1] S. H. Projects and W. Lovo, ―JMU Scholarly Commons Detecting credit card fraud : An analysis of fraud
detection techniques,‖ 2020.
[2] S. G and J. R. R, ―A Study on Credit Card Fraud Detection using Data Mining Techniques,‖ Int. J. Data Min.
Tech. Appl., vol. 7, no. 1, pp. 21–24, 2018, doi:10.20894/ijdmta.102.007.001.004.
[3] ―Credit Card Definition. ‖https://www.investopedia.com/terms/c/creditcard.asp(accessed Apr. 03, 2021).
[4] K. J. Barker, J. D‘Amato, and P. Sheridon, ―Credit card fraud: awareness and prevention,‖ J. Financ. Crime,
vol. 15, no. 4, pp. 398–410, 2008, doi:10.1108/13590790810907236.
[5] V. N. Dorada and S. Geetha, ―Credit Card Fraud Detection using Machine Learning Algorithms,‖ Procedia
Computer. Sci., vol. 165, pp. 631–641, 2019, doi: 10.1016/j.procs.2020.01.057.
[6] A. H. Alhazmi and N. Alekhine, ―A Survey of Credit Card Fraud Detection Use Machine Learning,‖ 2020 Int.
Conf. Computer. Inf. Technol. ICCIT 2020, pp. 10–15, 2020, doi: 10.1109/ICCIT-144147971.2020.9213809.
[7] B. Wickramanayake, D. K. Geeganage, C. Ouyang, and Y. Xu, ―A survey of online card payment fraud
detection using data mining-based methods,‖ arXiv, 2020.

20