scholarly journals Emerging Approach for Detection of Financial Frauds Using Machine Learning

2021 ◽  
pp. 9-22
Author(s):  
Upasana Mukherjee ◽  
Vandana Thakkar ◽  
Shawni Dutta ◽  
Utsab Mukherjee ◽  
Samir Kumar Bandyopadhyay
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Decision Tree ◽  
Credit Card ◽  
Fraud Detection ◽  
Loan Default ◽  
Credit Card Fraud ◽  
Detection Model ◽  
Default Prediction ◽  
Automated Process

The growth of regularly generated data from many financial activities has significant implications for every corner of financial modelling. This study has investigated the utilization of these continuous growing data by a means of an automated process. The automated process can be developed by using Machine learning based techniques that analyze the data and gain experience from the underlying data. Different important domains of financial fields such as Credit card fraud detection, bankruptcy detection, loan default prediction, investment prediction, marketing and many more can be modelled by implementing machine learning methods. Among several machine learning based techniques, the use of parametric and non-parametric based methods are approached by this research. Two parametric models namely Logistic Regression, Gaussian Naive Bayes models and two non-parametric methods such as Random Forest, Decision Tree are implemented in this paper. All the mentioned models are developed and implemented in the field of Credit card fraud detection, bankruptcy detection, loan default prediction. In each of the aforementioned cases, the comparative study among the classification techniques is drawn and the best model is identified. The performance of each classifier on each considered domain is evaluated by various performance metrics such as accuracy, F1-score and mean squared error. In the credit card fraud detection model the decision tree classifier performs the best with an accuracy of 99.1% and, in the loan default prediction and bankruptcy detection model, the random forest classifier gives the best accuracy of  97% and 96.84% respectively.

scholarly journals Emerging Approach for Detection of Financial Frauds Using Machine Learning

2021 ◽  
Author(s):  
Samir Bandyopadhyay ◽  
Vandana Thakkar ◽  
Upasana Mukherjee ◽  
Shawni Dutta
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Decision Tree ◽  
Credit Card ◽  
Fraud Detection ◽  
Loan Default ◽  
Credit Card Fraud ◽  
Detection Model ◽  
Default Prediction ◽  
Automated Process

The growth of regularly generated data from many financial activities has significant implications for every corner of financial modeling. This study has investigated the utilization of these continuous growing data by a means of an automated process. The automated process can be developed by using Machine learning based techniques that analyze the data and gain experience from the underlying data. Different important domains of financial fields such as Credit card fraud detection, bankruptcy detection, loan default prediction, investment prediction, marketing and many other financial models can be modeled by implementing machine learning models. Among several machine learning based techniques, the use of parametric and non-parametric based methods are approached by this research. Two parametric models namely Logistic Regression, Gaussian Naive Bayes models and two non-parametric methods such as Random Forest, Decision Tree are implemented in this paper. All the mentioned models are developed and implemented in the field of Credit card fraud detection, bankruptcy detection, loan default prediction. In each of the aforementioned cases, the comparative study among the classification techniques is drawn and the best model is identified. The performance of each classifier on each considered domain is evaluated by various performance metrics such as accuracy, recall, precision, F1-score and mean squared error. In the credit card fraud detection model the decision tree classifier performs the best with an accuracy of 99.1% and, in the loan default prediction and bankruptcy detection model, the random forest classifier gives the best accuracy of 97% and 96.84% respectively.

scholarly journals SUPERVISED MACHINE LEARNING ALGORITHMS FOR DETECTING CREDIT CARD FRAUD

2021 ◽  
pp. 131-134
Author(s):  
G.Bhargav Chowdari
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Logistic Regression ◽  
Random Forest ◽  
Decision Tree ◽  
Supervised Learning ◽  
Credit Card ◽  
Learning Algorithms ◽  
Learning Methods ◽  
Credit Card Fraud

One of the most serious ethical challenges in the credit card industry is fraud. Our paper’s major goal is to identify credit card theft and offer a reasonable solution to the problem. Credit card fraud has cost customers and banks billions of dollars around the world. Fraudsters are constantly attempting to come up with new ways and tricks to commit fraud, despite the fact that there are several measures in place to prevent it. Fraud detection is extremely important in the banking and finance industries. For detection purposes, we will use an artificial neural network. As a result, in order to prevent it, we will develop a system that will not only detect fraud, but will also detect it before it occurs. In order to detect new scams, our system will learn from previous frauds. Mining algorithms were used to detect fraud, but they failed miserably. We use machine learning methods to detect fraud in credit card transactions in our paper. The research employs supervised learning methods that are applied to a kaggle dataset that is severely skewed and imbalanced. We used robust scalar to balance the set, resulting in 51 percent non-fraud cases and 49 percent fraud ones. Logistic regression, random forest, decision tree, and KNN have all been implemented, with additional learning curves displaying which algorithm performs best. Accuracy, specificity, precision, and sensitivity are the evaluation criteria, and a comparative chart is created to show the comparative analysis of various supervised learning algorithms. KEYWORDS: KNN,Neural network,Logistic regression,Random forest,Decision tree

scholarly journals Credit Card Fraud Detection using Machine Learning and Deployment of Model in Public Cloud as a Web Service

2020 ◽  
Vol 9 (2) ◽  
pp. 548-552
Keyword(s):  
Machine Learning ◽  
Web Service ◽  
Credit Card ◽  
Detection System ◽  
Credit Cards ◽  
Fraud Detection ◽  
Machine Learning Algorithms ◽  
Credit Card Fraud ◽  
Detection Model ◽  
The World

In recent times, usage of credit cards has increased exponentially which has given way to an increase in the number of cybercrimes related to transactions using credit cards. In this paper, the aim is to reduce the fraudulent credit card transactions happening around the world. Latest technologies like machine learning algorithms, cloud computing and web service implementation has been used in this paper. The model uses Local outlier factor algorithm and Isolation forest algorithm to develop the credit card fraud detection model using unsupervised learning techniques. The model has been implemented as a Web service to make the solution integratable with other applications and clients across the world. A third party prototype application is developed and integrated to the Fraud Detection Model using Web Services. The complete Fraud Detection System is deployed on the cloud. The Fraud Detection Model shows exceptionally high accuracy when compared to other models already existing.

scholarly journals Credit Card Fraud Detection System

2020 ◽  
Vol 6 (12) ◽  
pp. 24-27
Author(s):  
Shashank Singh and Meenu Garg
Keyword(s):  
Machine Learning ◽  
Credit Card ◽  
Data Science ◽  
Detection System ◽  
Fraud Detection ◽  
Detection Problem ◽  
Credit Card Fraud ◽  
Local Outlier Factor ◽  
Local Outlier ◽  
Isolation Forest

It is essential that Visa organizations can distinguish false Mastercard exchanges so clients are not charged for things that they didn't buy. Such issues can be handled with Data Science and its significance, alongside Machine Learning, couldn't be more important. This undertaking expects to outline the demonstrating of an informational collection utilizing AI with Credit Card Fraud Detection. The Credit Card Fraud Detection Problem incorporates demonstrating past Visa exchanges with the information of the ones that ended up being extortion. This model is then used to perceive if another exchange is fake. Our target here is to identify 100% of the fake exchanges while limiting the off base misrepresentation arrangements. Charge card Fraud Detection is an average example of arrangement. In this cycle, we have zeroed in on examining and pre- preparing informational indexes just as the sending of numerous irregularity discovery calculations, for example, Local Outlier Factor and Isolation Forest calculation on the PCA changed Credit Card Transaction

Sign in / Sign up

Export Citation Format

Share Document