2021
DOI: 10.48550/arxiv.2112.04236
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Application of Deep Reinforcement Learning to Payment Fraud

Abstract: The large variety of digital payment choices available to consumers today has been a key driver of e-commerce transactions in the past decade. Unfortunately, this has also given rise to cybercriminals and fraudsters who are constantly looking for vulnerabilities in these systems by deploying increasingly sophisticated fraud attacks. A typical fraud detection system employs standard supervised learning methods where the focus is on maximizing the fraud recall rate. However, we argue that such a formulation can … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2023
2023
2023
2023

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(2 citation statements)
references
References 31 publications
0
2
0
Order By: Relevance
“…In addition, the authors make a comparison of several DRL algorithms on network intrusion detection datasets. Vimal et al [3] exploit a DQN to tackle the payment fraud detection problem and use the technology of experience replay to improve the efficiency of sampling.…”
Section: Deep Reinforcement Learning For Tabular Anomaly Detectionmentioning
confidence: 99%
See 1 more Smart Citation
“…In addition, the authors make a comparison of several DRL algorithms on network intrusion detection datasets. Vimal et al [3] exploit a DQN to tackle the payment fraud detection problem and use the technology of experience replay to improve the efficiency of sampling.…”
Section: Deep Reinforcement Learning For Tabular Anomaly Detectionmentioning
confidence: 99%
“…Tabular data refers to data that are arranged in the form of a table, in which each row represents a sample, and each column represents a feature. As the most common type of data in real-world applications, tabular data are widely used in many domains, such as network security [1,2], financial transaction [3,4], industrial manufacturing [5,6], marine traffic-cite [7,8], etc. Anomalies (also called outlier or novelty), which exist in almost all domain applications, often indicate malfunctions or malicious behavior and may result in property damage or even casualties.…”
Section: Introductionmentioning
confidence: 99%