• Corpus ID: 244954348

Application of Deep Reinforcement Learning to Payment Fraud

@article{Vimal2021ApplicationOD,
  title={Application of Deep Reinforcement Learning to Payment Fraud},
  author={Siddharth Vimal and Kanishka Kayathwal and Hardik Wadhwa and Gaurav Dhama},
  journal={ArXiv},
  year={2021},
  volume={abs/2112.04236}
}
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… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 52 REFERENCES
Deep learning detecting fraud in credit card transactions
TLDR
This analysis provides a comprehensive guide to sensitivity analysis of model parameters with regard to performance in fraud detection and presents a framework for parameter tuning of Deep Learning topologies for credit card fraud detection to enable financial institutions to reduce losses by preventing fraudulent activity.
Sequence classification for credit-card fraud detection
Deep Q-network-based adaptive alert threshold selection policy for payment fraud systems in retail banking
TLDR
The proposed approach formulates the threshold selection as a sequential decision making problem and uses Deep Q-Network based reinforcement learning and shows that this adaptive approach outperforms the current static solutions by reducing the fraud losses as well as improving the operational efficiency of the alert system.
Q-Credit Card Fraud Detector for Imbalanced Classification using Reinforcement Learning
TLDR
The Q-Credit Card Fraud Detector system classifies transactions into two classes: genuine and fraudulent and is built with artificial intelligence techniques comprising Deep Learning, Auto-encoder, and Neural Agents, elements that acquire their predicting abilities through a Qlearning algorithm.
Machine Learning For Credit Card Fraud Detection System
TLDR
The quick growth of the e-commerce industry led to an exponential growth in credit card online purchases, resulting in an increase in fraud, and the ability to predict the detection of fraud performance in the sampling has a significant impact on credit card transactions.
Deep Learning Methods for Credit Card Fraud Detection
TLDR
Experimental results show great performance of the proposed deep learning methods against traditional machine learning models and imply that the proposed approaches can be implemented effectively for real-world credit card fraud detection systems.
Using deep networks for fraud detection in the credit card transactions
  • Z. KazemiH. Zarrabi
  • Computer Science
    2017 IEEE 4th International Conference on Knowledge-Based Engineering and Innovation (KBEI)
  • 2017
TLDR
A deep autoencoder is proposed to extract best features from the information of the credit card transactions and then append a softmax network to determine the class labels and results can reveal the advantages of proposed method comparing to the state of the arts.
Fraud detection in banking using deep reinforcement learning
TLDR
The theory of Deep Reinforcement Learning is introduced, the history of DRL is introduced and two applications in banking are presented, which will discuss possible implementations.
A Time Attention based Fraud Transaction Detection Framework
TLDR
This work presents a novel method for detecting fraud transactions by leveraging patterns from both users' static profiles and users' dynamic behaviors in a unified framework to address and explore the information of users' behaviors in continuous time spaces.
...
...