Fraud Detection in Credit Card Transaction Using ANN and SVM

Shaji, Anchana; Binu, Sumitra; Nair, Akhil M.; George, Jossy P.

doi:10.1007/978-3-030-79276-3_14

Cited by 7 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In addition, RF ensemble yields an F1score of 99.19% after the application of the chi-squared feature selection approach; while other ensembles (i.e., Logistic Regression, KNN, Naïve Bayes, and Support Vector Machine) yielded an accuracy of 98.05%, 92.10%, 91.25% and 81.45% respectively. It is clearly observed and seen that the adaption of both the feature selection approach and SMOTE data balancing approach ensured improved accuracy when compared with the results yielded in the studies [46], [49], [104], [105]; This is as in Table 4, and also in agreement with [106], [107].…”

Section: Ensemble Performancesupporting

confidence: 77%

Enhancing the Random Forest Model via Synthetic Minority Oversampling Technique for Credit-Card Fraud Detection

Aghware,

Ojugo,

Adigwe

et al. 2024

J. Comput. Theor. Appl.

View full text Add to dashboard Cite

Fraudsters increasingly exploit unauthorized credit card information for financial gain, targeting un-suspecting users, especially as financial institutions expand their services to semi-urban and rural areas. This, in turn, has continued to ripple across society, causing huge financial losses and lowering user trust implications for all cardholders. Thus, banks cum financial institutions are today poised to implement fraud detection schemes. Five algorithms were trained with and without the application of the Synthetic Minority Over-sampling Technique (SMOTE) to assess their performance. These algorithms included Random Forest (RF), K-Nearest Neighbors (KNN), Naïve Bayes (NB), Support Vector Machines (SVM), and Logistic Regression (LR). The methodology was implemented and tested through an API using Flask and Streamlit in Python. Before applying SMOTE, the RF classifier outperformed the others with an accuracy of 0.9802, while the accuracies for LR, KNN, NB, and SVM were 0.9219, 0.9435, 0.9508, and 0.9008, respectively. Conversely, after the application of SMOTE, RF achieved a prediction accuracy of 0.9919, whereas LR, KNN, NB, and SVM attained accuracies of 0.9805, 0.9210, 0.9125, and 0.8145, respectively. These results highlight the effectiveness of combining RF with SMOTE to enhance prediction accuracy in credit card fraud detection.

show abstract

Section: Ensemble Performancesupporting

confidence: 77%

Enhancing the Random Forest Model via Synthetic Minority Oversampling Technique for Credit-Card Fraud Detection

Aghware,

Ojugo,

Adigwe

et al. 2024

J. Comput. Theor. Appl.

View full text Add to dashboard Cite

show abstract

“…Study [26] conducted experiments on the Credit Card Fraud Detection dataset using different machine learning algorithms to evaluate their performance. They compared five algorithms, including SVM, Naive Bayes, Logistic Regression, KNN, and Random Forest.…”

Section: Related Workmentioning

confidence: 99%

“…Selected Algorithms Efficient Algorithm Accuracy Kibria and Sevkli [17] LR, Deep Learning, and SVM Deep Learning 87.10% Naveen and Diwan [30] LR, QDA and SVM LR 99.38% Shaji et al [26] ANN and SVM, Both 88.00% Sinayobye et al [31] KNN, DT, RF, SVM, LR KNN 82.60% Btoush et al [32] Deep Learning DL 95.76% Taha et al [33] Optimized Light Gradient Boosting Machine OLGBM 98.40%…”

Section: Authorsmentioning

confidence: 99%

UNMASKING FRAUDSTERS: Ensemble Features Selection to Enhance Random Forest Fraud Detection

Akazue,

Debekeme,

Edje

et al. 2023

J. Comput. Theor. Appl.

View full text Add to dashboard Cite

Fraud detection is used in various industries, including banking institutes, finance, insurance, government agencies, etc. Recent increases in the number of fraud attempts make fraud detection crucial for safeguarding financial information that is confidential or personal. Many types of fraud problems exist, including card-not-present fraud, fake Marchant, counterfeit checks, stolen credit cards, and others. An ensemble feature selection technique based on Recursive feature elimination (RFE), Information gain (IG), and Chi-Squared (X2) in concurrence with the Random Forest algorithm, was proposed to give research findings and results on fraud detection and prevention. The objective was to choose the essential features for training the model. The Receiver Operating Characteristic (ROC) Score, Accuracy, F1 Score, and Precision are used to evaluate the model's performance. The findings show that the model can differentiate between fraudulent transactions and those that are not, with an ROC Score of 95.83% and an Accuracy of 99.6%. The F1 Score of 99.6%% and precision of 100% further sustain the model's ability to detect fraudulent transactions with the least false positives correctly. The ensemble feature selection technique reduced training time and did not compromise the model's performance, making it a valuable tool for businesses in preventing fraudulent transactions.

show abstract

“…Teori yang mendasari SVM sendiri sudah berkembang sejak 1960-an, tetapi baru diperkenalkan oleh Vapnik, Boser dan Guyon pada tahun 1992 dan sejak itu SVM berkembang dengan pesat. SVM adalah salah satu teknik yang relatif baru dibandingkan dengan teknik lain, tetapi memiliki performansi yang lebih baik di berbagai bidang aplikasi seperti pengenalan tulisan tangan, klasifikasi teks dan lain sebagainya [15]. SVM digunakan untuk mencari hyperplane terbaik dengan memaksimalkan jarak antar kelas.…”

Section: Support Vector Machineunclassified

Klasifikasi Transaksi Penipuan Pada Kartu Kredit Menggunakan Metode Resampling Dan Pembelajaran Mesin

Febriady

Samsuryadi

Rini

2022

mib

View full text Add to dashboard Cite

The high number of credit card fraud causes a lot of losses for both users and credit service providers. Because the rate of credit card transactions is very fast, it is necessary to detect credit card fraud as early as possible. However, another challenge that is no less important is the amount of data that is imbalanced between valid and invalid transactions. One solution to the problem of data imbalance is to use a resampling method that can improve the quantity of data so that the accuracy results are good. In this study, three types of resampling methods were implemented, SMOTE, bootstrap, and jackknife. Furthermore, to validate the success of the resampling method, three types of machine learning methods were used. The machine learning methods are SVM, ANN, and random forest. From the test results, it was found that the combination of resampling SMOTE and random forest methods produced the best performance with values of accuracy, precision, recall and F1-score of 99.95%, 81.63%, 90.91% and 86.02%, respectively.

show abstract

Fraud Detection in Credit Card Transaction Using ANN and SVM

Cited by 7 publications

References 15 publications

Enhancing the Random Forest Model via Synthetic Minority Oversampling Technique for Credit-Card Fraud Detection

Enhancing the Random Forest Model via Synthetic Minority Oversampling Technique for Credit-Card Fraud Detection

UNMASKING FRAUDSTERS: Ensemble Features Selection to Enhance Random Forest Fraud Detection

Klasifikasi Transaksi Penipuan Pada Kartu Kredit Menggunakan Metode Resampling Dan Pembelajaran Mesin

Contact Info

Product

Resources

About