IRJET- Credit Card Fraud Detection Techniques (original) (raw)
Related papers
Erzincan University Journal of Science and Technology, 2022
A credit card is an important financial tool that has emerged in parallel with the developments in technology from the past to the present and has become an indispensable part of human life. The credit card has many advantages that can be listed as facilitating online shopping, providing installments in purchases, and preventing cash dependence. This is why the rate of use of credit cards worldwide is increasing day by day. On the other hand, there are some risks of the credit cards highlighted by security concerns. The fraudsters who access the identity and credit card information of the consumers through different means use it to shop online without the consumer's knowledge and gain an unfair advantage. Therefore, it is crucial to eliminate this security vulnerability that the fraudsters exploit and to develop an effective solution to the customer victimization experienced by e-commerce companies due to the fraudulent credit card transactions. With this motivation, the performance of the methods from different research fields was examined to explore the solution space in detail in terms of the problem at hand within the scope of this study. For this purpose, three machine learning algorithms (K-Nearest Neighbor, Naive Bayes, Support Vector Machine), two artificial neural network algorithms (Binary Classifier, Autoencoder), and two deep learning algorithms (Deep Autoencoder and Deep Neural Network Classifier) were implemented. The effectiveness of the algorithms in question was tested with a famous dataset widely used in the literature. Experimental results showed that the Deep Neural Network Classifier outperformed the other algorithms used in this study and the best study ever reported in the literature in detecting fraudulent credit card transactions when accuracy and AUROC performance criteria were taken into account.
IRJET, 2021
Credit Card fraud is a sort of identity theft where thieves acquire or receive cash advances from another user's credit card account. This may occur through the use of a user's current accounts, physical credit card robbery, account number or PINs, or through the opening of an unknown credit card account in the user name. The Credit Card fraud detection project identifies the fraudulent nature of the new transaction by shaping the credit card transactions with the knowledge of those which have been fraudulent. In order to detect, if a transaction is a normal payment or a fraud, we will employ several predictive models. The strategies for classification are promising ways to identify fraud and non-fraud transactions. Sadly, classifying techniques do not work well in certain circumstances when it comes to big disparities in data distribution. In our work, we will be applying Machine-Learning algorithms: Logistic Regression, SVM, Naive Bays, Decision Trees, Random Forests and Deep Learning algorithm to predict fraud through Artificial Neural Networks. Results are analysed and compared.
Credit card fraud detection, anomaly detection, applications of machine learning, Machine learning
IAEME PUBLICATION, 2020
Credit card fraud refers to the physical loss of credit card or loss of sensible credit card data. Several machine-learning algorithms can be applied for detection of false credit card activities. Financial fraud is an ever-growing threat, with real results in the business activity. Machine learning had performed an essential role in the discovery of credit card fraud in online transactions. The performance of fraud detection in credit card transactions is influenced by the sampling method on the dataset, collection of variables and detection technique(s) applied. Consequently, applications of detecting credit card frauds are increasing for high-value banks and financial institutions on demand. False activities can happen in many ways and can place into several categories. Financial fraud, such as money laundering, is a severe process of crime that makes illegitimately obtained funds go to terrorism or other criminal activity. The primary issue when it happens to represent fraud detection as a classification difficulty comes from the reality that in real-world data, the majority of transactions are not false. This variety of unauthorised action requires complex networks of business and financial transactions, which perform it challenging to detect fraud entities and find the characteristics of fraud. In this paper, the class imbalance problem is handled by finding legal or fraud transaction using advanced bidirectional Gated recurrent unit (ABiGRU) based machine learning algorithm. Also, suggesting advanced frequent pattern mining algorithm. It can leverage both network data and function data for the detection of financial fraud and very opportunity presented using the best machine learning paradigm. The experimental results illustrate that the proposed scheme provides better accuracy compared with the previous algorithms..
Credit Card Fraud Detection using Deep Learning Techniques
Informatica Economica, 2021
Credit card fraud is an event problem and fraud detecting techniques getting more sophisticated each day. Mainly internet is becoming more common in almost every domain. Online transactions, shopping, and e-commerce are expanding step by step. Due to which in the online payment system, fraudulent activities have also increased. It has cost banks and their customers a loss of billions of rupees. The techniques used now a day detects the anomaly only after the fraud transaction takes place. The intruders have found ways to crack the system loopholes and defeat the security. These frauds are not consistent in their actions, they constantly alter. Thus, Artificial Intelligent (AI) algorithms are used to detect the behavior of such activity by learning the past behavior of the transaction of the users. An unsupervised algorithm is used to detect online transactions, as fraudsters commit fraud once by online media and then move on to other techniques. This paper discusses the performance analysis and the comparative study of the two Deep Learning algorithms which include auto-encoder and the neural network. In this paper accuracy, precision, recall, and AUC curve are considered as a model evaluation factor.
IRJET, 2020
In these days, due to technology enhancement the credit card became a very common and popular item instead of carrying physical currency. It helps in providing cashless shopping over the globe. Extortion function happens only during on the web installment as Master Card number is adequate to make an exchange which will be on the Visa to make online payment however for disconnected installment secret phrase will be asked souring disconnected exchange fakes can't happen. The proposed framework's main necessity of identification of fraudulent transaction of all the transactions made through credit cards. The proposed framework is mentioned implemented through various popular machine learning algorithms such as KNN, logistic regression, SVM, decision tree, and random forest. The proposed framework was implemented on the famous dataset which was freely available on Kaggle. Overall, we got 100 % accuracy after using Lasso feature selection with various machine algorithms.
International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2022
Development of communication technologies and ecommerce has made the credit card as the most common technique of payment for both online and regular purchases. So, security in this system is highly expected to prevent fraud transactions. Fraud transactions in credit card data transaction are increasing each year. In this direction, researchers are also trying the novel techniques to detect and prevent such frauds. However, there is always a need of some techniques that should precisely and efficiently detect these frauds. This paper proposes a scheme for detecting frauds in credit card data which uses a Neural Network (NN) based unsupervised learning technique. Proposed method outperforms the existing approaches of Auto Encoder (AE), Local Outlier Factor (LOF), Isolation Forest (IF) and K-Means clustering. Proposed NN based fraud detection method performs with 99.87% accuracy whereas existing methods AE, IF, LOF and K Means gives 97?, 98?, 98? and 99.75? accuracy respectively.
International Journal of Advanced Computer Science and Applications
Frauds have no constant patterns. They always change their behavior; so, we need to use an unsupervised learning. Fraudsters learn about new technology that allows them to execute frauds through online transactions. Fraudsters assume the regular behavior of consumers, and fraud patterns change fast. So, fraud detection systems need to detect online transactions by using unsupervised learning, because some fraudsters commit frauds once through online mediums and then switch to other techniques. This paper aims to 1) focus on fraud cases that cannot be detected based on previous history or supervised learning, 2) create a model of deep Auto-encoder and restricted Boltzmann machine (RBM) that can reconstruct normal transactions to find anomalies from normal patterns. The proposed deep learning based on auto-encoder (AE) is an unsupervised learning algorithm that applies backpropagation by setting the inputs equal to the outputs. The RBM has two layers, the input layer (visible) and hidden layer. In this research, we use the Tensorflow library from Google to implement AE, RBM, and H2O by using deep learning. The results show the mean squared error, root mean squared error, and area under curve.
Investigation of credit cards fraud detection by using deep learning and classification algorithms
2020
Criminal financial behaviour is a problem for both banks and newly created fintech companies. Credit card fraud detection becomes a challenge for any such company. The aim of this paper is to compare ability to detect credit card fraud by four algorithmic methods: Generalized method of moments, Knearest neighbour, Naive Bayes classification and Deep learning. The deep learning algorithm has been tuned to select key parameters so that fraud detection accuracy is the best. Five recognition accuracy parameters and a cost calcualtions showed that the deep learning algorithm is the best fraud detection method compared to other classification algorithms. A financial company reduces losses and increases customer confidence by using fraud prevention technologies.
A Review of deep learning techniques in detection of anomaly in credit card transaction
IRJET, 2022
Credit card fraud is a common occurrence that causes enormous financial losses. Online purchases have dramatically expanded, and a major portion of those purchases are made using credit cards. As a result, banks and other financial organizations fund the development of software that identify credit card fraud. Fraudulent transactions can occur in a variety of ways and fall under a number of distinct categories. Credit card firms need to identify fraudulent credit card transactions in order to avoid having their customers’ accounts charged for goods they did not buy. Machine learning and data science aid in resolving these problems. The legal transactions are mixed in with the fraudulent transactions, so it is impossible to effectively identify the fraudulent transactions using simple identification approaches that compare both the fraudulent and legitimate data. With the use of credit card fraud detection, this research aims to demonstrate the modelling of a knowledge set using machine learning. Our objective is to eliminate erroneous fraud classifications while detecting 100% of fraudulent transactions. A typical categorization sample would be credit card fraud detection. On the PCA converted Credit Card Transaction data, we concentrated on analyzing and pre-processing data sets, as well as deploying numerous anomaly detection techniques such as the Local Outlier Factor and Isolation Forest algorithm, as well as one class SVM (Support Vector Machine)
ANN Deep Learning and Random Forest Model for Fraud Detection of Credit Card Users In Banking System
International Journal of Scientific Research in Science, Engineering and Technology, 2020
A Detection device offers signs and signs of sickness in competition to invasion attacks (in which/during which/in what way/in what) an ordinary firewall fails. Device learning sets of computer instructions purpose to find out (weird, unexpected things) using supervised and unsupervised (success plans/ways of reaching goals). Abilities desire (success plans/ways of reaching goals) identify extremely important abilities and get rid of beside the factor and unnecessary attributes to lessen the interesting quality of (typical and expected) location. This paintings offers an abilities preference (solid basic structure on which bigger things can be built) for inexperienced community (weird, unexpected thing) detection the use of fantastic device learning classifiers. The (solid basic structure on which bigger things can be built) applies clearly stated/particular ways of doing things with the helpful helpful helpful useful useful thing/valuable supply of the use of clear out and wrapper functions preference ways of doing things. The reason of this (solid basic structure on which bigger things can be built) is to pick out the (almost nothing/very little) shape of functions that advantage the awesome (quality of being very close to the truth or true number). Dataset is used in the experimental effects to test/evaluate the proposed (solid basic structure on which bigger things can be built). The results display that through way of using 18 abilities from one of the clean out rating ways of doing things and using ann and childlike (because of a lack of understanding) bayes as a classifier, a (quality of being very close to the truth or true number) of 86% is completed and compare result with Random Forest and Decision Tree.