Scribd
Upload
9 views

Presentation database

Data about presentation of college

Uploaded by

rakesh1890
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
9 views

Presentation database

Data about presentation of college

Uploaded by

rakesh1890
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 9

Credit card fraud detection

Submitted by
Miss sakshi Rajendra sisode

Guided by
Dr.Rakesh S deore
Head
Department of computer science
Contents
 Introduction
 Literature Review
 Methodology
 Evaluation
 Conclusion
 References
Introduction

Credit card fraud refers to unauthorized use of a credit card or its details to make transactions or gain access to funds
without the owner's consent. It is a significant challenge in the financial sector, causing billions of dollars in losses
annually and undermining trust in electronic payment systems.Definition: Credit card fraud involves deceitful activities
performed by individuals or groups to illegally obtain goods, services, or money using another person’s credit card
information.

Credit Card Fraud Detection Using Machine Learning Algorithms


Authors: D. Y. Lee, S. Y. Chang, and S. Y. Choi
Publication: Proceedings of the International Conference on Information and Communication Technology
Convergence
ICTC), 2017.
Summary: This paper presents an in-depth analysis of various machine learning algorithms, such as
Logistic Regression,
decision Trees, and Random Forest, for detecting credit card fraud. It evaluates the models' effectiveness
on imbalanced
datasets, highlighting the challenges and the importance of feature selection and pre-processing in
improving model
performance.
Literature review

Types of Credit Card Fraud Detection:


1. Card-Present (CP) Fraud:
This type of fraud involves the physical presence of a stolen or counterfeit
credit card during a transaction.

2. . Card-Not-Present (CNP) Fraud:


CNP fraud occurs during transactions where the physical card is not required,
such as online or over-the-phone purchases.

3. Identity Theft:
Fraudsters steal personal information to impersonate the victim and access
their credit card account or create new accounts in their name .

4. Account Takeover:
In account takeover fraud, criminals gain unauthorized access to an existing
methodology

• Understand the Dataset


• Handling Missing Data
• Feature Scaling
• Encoding Categorical Features
• Identify Missing Data
• Assess the Impact of Missing Data
• Class Distribution (Fraud vs. Non-Fraud)
• Box Plot: Transaction Amount for Fraud vs. Non-Fraud
• Analyzing Feature Correlations:
evaluation

1. Precision
•Definition:
•Precision measures how many of the transactions predicted as fraudulent by
the model are actually fraudulent.
•2. Recall
•Definition:
•Recall measures how many of the actual fraudulent transactions the model is
able to correctly identify.​
•
•3. F1 Score
•Definition:
•The F1 score is the harmonic mean of precision and recall, combining both
metrics into a single number.
conclusion

Neural Networks emerged as the best-performing model in terms


of accuracy, AUC, precision, recall, and F1 score. This suggests
that deep learning models are highly capable of capturing complex
patterns in fraud detection tasks, particularly with large datasets.
Gradient Boosting and Random Forest also demonstrated high
performance across multiple metrics, excelling in terms of both
predictive accuracy and ability to handle imbalanced datasets,
making them strong contenders for fraud detection.
refernces

• Fraud Detection in Retail Dataset (Azure AI)


• Description: This dataset from Microsoft Azure AI contains fraud
detection data in a retail setting. It includes transaction and
customer data, and labels fraudulent transactions for use in
machine learning.
• Features: Information on customer demographics, transaction
history, and payment methods.
• Link: Azure AI Fraud Detection Dataset.
Thank you

You might also like