Sequential credit card fraud detection: A joint deep neural network and probabilistic graphical model approach

2021 ◽  
Javad Forough ◽  
Saeedeh Momtazi
Souad Larabi Marie-Sainte ◽  
Mashael Bin Alamir ◽  
Deem Alsaleh ◽  
Ghazal Albakri ◽  
Jalila Zouhair

Khalid I. Alkhatib ◽  
Ahmad I. Al-Aiad ◽  
Mothanna H. Almahmoud ◽  
Omar N. Elayan

Aruna Kumar Joshi ◽  
Vikram Shirol ◽  
Shreekanth Jogar ◽  
Pavankumar Naik ◽  
Annapoorna Yaligar

Credit Card Fraud is one of the major moral issues in the public and private bans sector. The effect of this problems leads to the several ethical trouble. The important themes are to notice the distinctive kinds of credit card fraud and to locate different methods that have been used in fraud detection. The sub-point is to suppose about existing and ruin down as of late dispensed discoveries in fraud detection. Probable upon the variety of extortion appeared with the banks or different financial organizations, exceptional measures can be embraced and executed. The work carried out in this paper are usually going to have really beneficial residences as a approaches as expenditure reserve fund and time capability. The cost utilization of the strategies investigated proper right here is in the minimization of credit card fraud. Anyway, there are up to now moral troubles when appropriate credit card customers are unsorted as fraudulent. Credit Card Fraud Detection is an method which will help people for their transaction process in shopping mall and any other transaction process nowadays fraud detection is nothing but an process where the criminals are found and there are many illegal activities are taking place which causes difficulty for people. Here in this paper we are using SMOTE technique to find fraud and this technique will help to sort both the normal transaction and fraud transaction this process can make easy to find fraudulent. And Neural Network KNN are also taken place to find Credit Card Fraud.

E. Aleskerov ◽  
B. Freisleben ◽  
B. Rao

Saurabh C. Dubey ◽  
Ketan S. Mundhe ◽  
Aditya A. Kadam

Aman Gulati ◽  
Prakash Dubey ◽  
C MdFuzail ◽  
Jasmine Norman ◽  
R Mangayarkarasi

2020 ◽  
Vol 34 (01) ◽  
pp. 362-369 ◽  
Dawei Cheng ◽  
Sheng Xiang ◽  
Chencheng Shang ◽  
Yiyi Zhang ◽  
Fangzhou Yang ◽  

Credit card fraud is an important issue and incurs a considerable cost for both cardholders and issuing institutions. Contemporary methods apply machine learning-based approaches to detect fraudulent behavior from transaction records. But manually generating features needs domain knowledge and may lay behind the modus operandi of fraud, which means we need to automatically focus on the most relevant patterns in fraudulent behavior. Therefore, in this work, we propose a spatial-temporal attention-based neural network (STAN) for fraud detection. In particular, transaction records are modeled by attention and 3D convolution mechanisms by integrating the corresponding information, including spatial and temporal behaviors. Attentional weights are jointly learned in an end-to-end manner with 3D convolution and detection networks. Afterward, we conduct extensive experiments on real-word fraud transaction dataset, the result shows that STAN performs better than other state-of-the-art baselines in both AUC and precision-recall curves. Moreover, we conduct empirical studies with domain experts on the proposed method for fraud post-analysis; the result demonstrates the effectiveness of our proposed method in both detecting suspicious transactions and mining fraud patterns.

2019 ◽  
Sevdalina Georgieva ◽  
Maya Markova ◽  
Velizar Pavlov

2021 ◽  
Vol 36 (1) ◽  
pp. 277-280
S. Ravi ◽  
J. Thanga Kumar ◽  
Dr. Linda Joseph ◽  
Sumanth Raju Kunjeti ◽  
Nandu Vardhan Saniboina ◽  

Internet based business, e-Services and numerous other web-based application have expanded the online payment modes, expanding the danger for online frauds. Expansion in fraud rates, analysts began utilizing distinctive machine learning strategies to identify and dissect frauds in online exchanges. The principle point of the paper is to plan and build up a novel fraud identification strategy for Streaming Transaction Data, with a target, to dissect the previous exchange subtleties of the clients and concentrate the personal conduct standards. This paper proposes a canny model for detecting fraud in credit card exchange datasets that are unusually imbalanced and enigmatic. The class irregularity issue is dealt with by finding lawful just as fraud exchange designs for every client by utilizing continuous itemset mining.

Sign in / Sign up

Export Citation Format

Share Document