Fraud Detection using Machine Learning and Deep Learning

Pradheepan Raghavan; Neamat El Gayar

doi:10.1109/ICCIKE47802.2019.9004231

Fraud Detection using Machine Learning and Deep Learning

Pradheepan Raghavan, Neamat El Gayar

School of Mathematical & Computer Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

87 Citations (Scopus)

Abstract

Frauds are known to be dynamic and have no patterns, hence they are not easy to identify. Fraudsters use recent technological advancements to their advantage. They somehow bypass security checks, leading to the loss of millions of dollars. Analyzing and detecting unusual activities using data mining techniques is one way of tracing fraudulent transactions. transactions. This paper aims to benchmark multiple machine learning methods such as k-nearest neighbor (KNN), random forest and support vector machines (SVM), while the deep learning methods such as autoencoders, convolutional neural networks (CNN), restricted boltzmann machine (RBM) and deep belief networks (DBN). The datasets which will be used are the European (EU) Australian and German dataset. The Area Under the ROC Curve (AUC), Matthews Correlation Coefficient (MCC) and Cost of failure are the 3-evaluation metrics that would be used.

Original language	English
Title of host publication	2019 International Conference on Computational Intelligence and Knowledge Economy (ICCIKE)
Publisher	IEEE
Pages	334-339
Number of pages	6
ISBN (Electronic)	9781728137780
DOIs	https://doi.org/10.1109/ICCIKE47802.2019.9004231
Publication status	Published - 20 Feb 2020
Event	2019 International Conference on Computational Intelligence and Knowledge Economy - Dubai, United Arab Emirates Duration: 11 Dec 2019 → 12 Dec 2019

Conference

Conference	2019 International Conference on Computational Intelligence and Knowledge Economy
Abbreviated title	ICCIKE 2019
Country/Territory	United Arab Emirates
City	Dubai
Period	11/12/19 → 12/12/19

Keywords

autoencoder
convolutional neural networks
credit card
deep belief networks
deep learning
fraud detection
k nearest neighbor
machine learning
random forest
restricted boltzmann machine
support vector machine

ASJC Scopus subject areas

Artificial Intelligence
Computer Science Applications

Access to Document

10.1109/ICCIKE47802.2019.9004231

Cite this

@inproceedings{ef2a28b157fd43f3b57b6a70b474c875,

title = "Fraud Detection using Machine Learning and Deep Learning",

abstract = "Frauds are known to be dynamic and have no patterns, hence they are not easy to identify. Fraudsters use recent technological advancements to their advantage. They somehow bypass security checks, leading to the loss of millions of dollars. Analyzing and detecting unusual activities using data mining techniques is one way of tracing fraudulent transactions. transactions. This paper aims to benchmark multiple machine learning methods such as k-nearest neighbor (KNN), random forest and support vector machines (SVM), while the deep learning methods such as autoencoders, convolutional neural networks (CNN), restricted boltzmann machine (RBM) and deep belief networks (DBN). The datasets which will be used are the European (EU) Australian and German dataset. The Area Under the ROC Curve (AUC), Matthews Correlation Coefficient (MCC) and Cost of failure are the 3-evaluation metrics that would be used.",

keywords = "autoencoder, convolutional neural networks, credit card, deep belief networks, deep learning, fraud detection, k nearest neighbor, machine learning, random forest, restricted boltzmann machine, support vector machine",

author = "Pradheepan Raghavan and Gayar, {Neamat El}",

year = "2020",

month = feb,

day = "20",

doi = "10.1109/ICCIKE47802.2019.9004231",

language = "English",

pages = "334--339",

booktitle = "2019 International Conference on Computational Intelligence and Knowledge Economy (ICCIKE)",

publisher = "IEEE",

address = "United States",

note = "2019 International Conference on Computational Intelligence and Knowledge Economy, ICCIKE 2019 ; Conference date: 11-12-2019 Through 12-12-2019",

}

Raghavan, P & Gayar, NE 2020, Fraud Detection using Machine Learning and Deep Learning. in 2019 International Conference on Computational Intelligence and Knowledge Economy (ICCIKE). IEEE, pp. 334-339, 2019 International Conference on Computational Intelligence and Knowledge Economy, Dubai, United Arab Emirates, 11/12/19. https://doi.org/10.1109/ICCIKE47802.2019.9004231

TY - GEN

T1 - Fraud Detection using Machine Learning and Deep Learning

AU - Raghavan, Pradheepan

AU - Gayar, Neamat El

PY - 2020/2/20

Y1 - 2020/2/20

N2 - Frauds are known to be dynamic and have no patterns, hence they are not easy to identify. Fraudsters use recent technological advancements to their advantage. They somehow bypass security checks, leading to the loss of millions of dollars. Analyzing and detecting unusual activities using data mining techniques is one way of tracing fraudulent transactions. transactions. This paper aims to benchmark multiple machine learning methods such as k-nearest neighbor (KNN), random forest and support vector machines (SVM), while the deep learning methods such as autoencoders, convolutional neural networks (CNN), restricted boltzmann machine (RBM) and deep belief networks (DBN). The datasets which will be used are the European (EU) Australian and German dataset. The Area Under the ROC Curve (AUC), Matthews Correlation Coefficient (MCC) and Cost of failure are the 3-evaluation metrics that would be used.

AB - Frauds are known to be dynamic and have no patterns, hence they are not easy to identify. Fraudsters use recent technological advancements to their advantage. They somehow bypass security checks, leading to the loss of millions of dollars. Analyzing and detecting unusual activities using data mining techniques is one way of tracing fraudulent transactions. transactions. This paper aims to benchmark multiple machine learning methods such as k-nearest neighbor (KNN), random forest and support vector machines (SVM), while the deep learning methods such as autoencoders, convolutional neural networks (CNN), restricted boltzmann machine (RBM) and deep belief networks (DBN). The datasets which will be used are the European (EU) Australian and German dataset. The Area Under the ROC Curve (AUC), Matthews Correlation Coefficient (MCC) and Cost of failure are the 3-evaluation metrics that would be used.

KW - autoencoder

KW - convolutional neural networks

KW - credit card

KW - deep belief networks

KW - deep learning

KW - fraud detection

KW - k nearest neighbor

KW - machine learning

KW - random forest

KW - restricted boltzmann machine

KW - support vector machine

UR - http://www.scopus.com/inward/record.url?scp=85080884098&partnerID=8YFLogxK

U2 - 10.1109/ICCIKE47802.2019.9004231

DO - 10.1109/ICCIKE47802.2019.9004231

M3 - Conference contribution

AN - SCOPUS:85080884098

SP - 334

EP - 339

BT - 2019 International Conference on Computational Intelligence and Knowledge Economy (ICCIKE)

PB - IEEE

T2 - 2019 International Conference on Computational Intelligence and Knowledge Economy

Y2 - 11 December 2019 through 12 December 2019

ER -

Fraud Detection using Machine Learning and Deep Learning

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this