Analysis of Various Credit Card Fraud Detection Techniques

2021 ◽  
pp. PP. 13-20
Author(s):  
admin admin ◽  

Data mining is a technique that is applied to mine valuable information from the rough data. A prediction analysis is an approach that has the potential for forecasting future possibilities based on the recent data. The CCFD is the challenge of prediction in which fraudulent transactions are predicted based on certain rules. There are several stages included in the detection of fraud in credit cards. Various classification algorithms are reviewed with respect to the performance analysis in order to detect fraud in the credit card. The performance is measured with regard to precision.

2019 ◽  
Vol 8 (11) ◽  
pp. 24878-24882 ◽  
Author(s):  
Mandeep Singh ◽  
Sunny Kumar ◽  
Sunny Kumar ◽  
Tushant Garg

Now a day the usage of credit cards and net banking for online payments has dramatically increased. The most popular mode of online as well as regular purchase payments is through credit card and security of such transactions is also a major issue as frauds are increasing rapidly. In the existing scenario, fraud is detected after the transaction is done and it makes more difficult to find out fraudulent loses barred by issuing authority. In this paper, we observe the behaviour of credit card transactions using a Hidden Markov Model (HMM) and show how it detects frauds. An HMM is initially trained with the normal behaviour of transaction. If the present credit card transaction is not accepted by the trained HMM with enough high probability, then it declares as a fraudulent transaction. At the same time, we try to ensure that no genuine transactions are rejected.


2021 ◽  
Vol 23 (06) ◽  
pp. 318-344
Author(s):  
Amit Pundir ◽  
◽  
Rajesh Pandey ◽  

Misrepresentation of money is a developing issue in monetary business with far-reaching consequences and keeping in mind that many processes have been found. Data quality management with data mining has been effectively applied to data sets to mechanize the investigation of massive amounts of complex information. Data mining has likewise played a notable role in identifying credit card fraud in online exchanges. Fraud detection in credit cards is a data quality management issue that considered under data mining, tested for two important reasons — first, the profiles of ordinary and false practices habitually change, and also because of the explanation that charge card fraud information is exceptionally slow. This research paper examines the performance of Decision Trees, Logistics Regression, and Random Forest rely strategically on profoundly skewed credit card fraud data. The dataset of credit card transactions is sourced from Kaggle (a publically accessible dataset repository) with 284,807 transactions. These methods are applied to raw data values and data preprocessing techniques. Assessment of the performance of techniques depends on accuracy, sensitivity, specificity, precision, and recall. Results indicate the optimal accuracy for the decision trees, logistics regression, and random forest classifiers with 90.8%, 98.5%, and 99.1% respectively.


Author(s):  
Nikita Shirodkar ◽  
Pratikesh Mandrekar ◽  
Rohit Shet Mandrekar ◽  
Rahul Sakhalkar ◽  
K.M. Chaman Kumar ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document