Analysis of Credit Card Fraud detection using Machine Learning models on balanced and imbalanced datasets

doi:10.30534/ijeter/2021/02972021

Cited by 8 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A two-by-two matrix may show a binary classifier's four possible results. These findings are "TN," "FN," "TP," and "FP" [12]. A two-way classification table is crucial.…”

Section: Results and Discusionmentioning

confidence: 99%

“…The problem set is very difficult for machine learning systems to tackle for a number of different reasons, including the fact that the data is seasonal and skew. A kind of machine learning recognized as long short-term memory networks was used by [11] in order to recognise fraudulent transactions and differentiate them from authentic ones developed an approach that makes use of neural network classifiers in conjunction with bayesian networks in order to determine whether or not a credit card transaction included fraudulent activity [12,13]. Additionally record a variety of fraudulent acts using credit cards and maintain a constant awareness of the most cutting-edge deception techniques that fraudsters may utilize the first to present the idea of quantifying the degree to which the performance of a machine learning method might vary [14].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Identifying Potentially Fraudulent Credit Card Transactions with the use of Soft Computing Methods

Venkatesan¹

2023

IJSMIEN

View full text Add to dashboard Cite

One of the most pervasive difficulties facing modern finance organisations, corporations, and governments is the alarming rise in fraudulent or dishonest practises around financial transactions, especially those using credit cards. As difficulties go, this is one of the more prevalent ones. To protect the interests of both consumers and businesses, it is crucial to implement a fraud detection system that heavily relies on the use of intelligent fraud detection tactics. Numerous fraud detection methods, strategies, and systems have been reported in the scholarly literature; many of them make use of intelligent strategies like algorithms and frameworks. This project begins out with an exploratory data analysis aimed at identifying potentially fraudulent credit card transactions. The authors next provide some categorization models that are implemented in soft computing by means of ingenious methodologies. For the aim of evaluation, several other classification algorithms such decision trees, random forests, and logistic regressions have been used in addition to the Knearest neighbour (K-NN) technique. The suggested model provides a more accurate, computationally efficient, and lightweight option for detecting credit card fraud.

show abstract

“…A two-by-two matrix may show a binary classifier's four possible results. These findings are "TN," "FN," "TP," and "FP" [12]. A two-way classification table is crucial.…”

Section: Results and Discusionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Identifying Potentially Fraudulent Credit Card Transactions with the use of Soft Computing Methods

Venkatesan¹

2023

IJSMIEN

View full text Add to dashboard Cite

show abstract

“…As a result, the overall credit card fraud dataset becomes highly skewed, with only a few examples of one class. In the previous credit card fraud detection, the impact of this extremely imbalanced situation was ignored (Mallidi, et al, 2021), (Ali, et al, 2015). When a credit card was first used to make a transaction in the early 1970s, with a slide machine it was processed manually which imprinted the credit card number on a multi-part receipt.…”

Section: Introductionmentioning

confidence: 99%

Handling Class Imbalance in Credit Card Fraud Using Various Sampling Techniques

Khatun¹,

Alam²,

Taslim³

et al. 2022

Am. J. Multidis. Res. Innov.

View full text Add to dashboard Cite

Over the last few decades, credit card fraud (CCF) has been a severe problem for both cardholders and card providers. Credit card transactions are fast expanding as internet technology advances, significantly relying on the internet. With advanced technology and increased credit card usage, fraud rates are becoming a problem for the economy. However, the credit card dataset is highly imbalanced and skewed. Many classification techniques are used to classify fraud and non-fraud but in a certain condition, they may not generate the best results. Different types of sampling techniques such as under-over sampling, Synthetic Minority Oversampling, and Adaptive synthetic techniques have been used to overcome the class imbalance problem in the credit card dataset. Then, the sampled datasets are classified using different machine learning techniques like Decision Tree, Random Forest, K-Nearest Neighbors, Logistic Regression, and Naive Bayes. Recall, F1- score, accuracy, precision, and error rate used to evaluate the model performance. The Logistic Regression model achieved the highest result with 99.94% after under sampling techniques and Random Forest model achieved the highest result with 99.964% after over sampling techniques.

show abstract

“…This assumption is not always valid for many real-world applications from medical diagnosis, fraud detection, information retrieval, and so on. In training data, if there is a much lower number of instances of one class, then the assumed priority distribution for classification will be hindered and this classification paradigm will be termed as imbalance classification [2] [24].…”

Section: Introductionmentioning

confidence: 99%

A Survey on Imbalanced Data Handling Techniques for Classification

2021

IJETER

View full text Add to dashboard Cite

Classification is a supervised learning task based on categorizing things in groups on the basis of class labels. Algorithms are trained with labeled datasets for accomplishing the task of classification. In the process of classification, datasets plays an important role. If in a dataset, instances of one label/class (majority class) are much more than instances of another label/class (minority class), such that it becomes hard to understand and learn characteristics of minority class for a classifier, such dataset is termed an imbalanced dataset. These types of datasets raise the problem of biased prediction or misclassification in the real world, as models based on such datasets may give very high accuracy during training, but as not familiar with minority class instances, would not be able to predict minority class and thus fails poorly. A survey on various techniques proposed by the researchers for handling imbalanced data has been presented and a comparison of the techniques based on f-measure has been identified and discussed.

show abstract

Analysis of Credit Card Fraud detection using Machine Learning models on balanced and imbalanced datasets

Cited by 8 publications

References 13 publications

Identifying Potentially Fraudulent Credit Card Transactions with the use of Soft Computing Methods

Identifying Potentially Fraudulent Credit Card Transactions with the use of Soft Computing Methods

Handling Class Imbalance in Credit Card Fraud Using Various Sampling Techniques

A Survey on Imbalanced Data Handling Techniques for Classification

Contact Info

Product

Resources

About