A Novel Approach for Credit Card Fraud Detection using Decision Tree and Random Forest Algorithms

Dileep, M. R.; Navaneeth, A V; Abhishek, M R

doi:10.1109/icicv50876.2021.9388431

Cited by 31 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Penelitian terkait deteksi transaksi fraud kartu kredit telah dilakukan oleh beberapa peneliti dengan melakukan pengembangan model menggunakan algoritma berbasis supervised learning seperti SVM, Naïve Bayes, Logistic Regression, Decision Tree, KNN, Random Forest, GBM, LightGBM, XGBoost, AdaBoost, serta CatBoost (Taha and Malebary, 2020) (Dileep, Navaneeth and Abhishek, 2021) (Sumanth et al, 2022) (Alfaiz and Fati, 2022) (Madhurya et al, 2022). Pendekatan untuk mengatasi data tidak seimbang pernah dilakukan dengan teknik resampling seperti Random Oversampling, SMOTE dan ADASYN oleh beberapa peneliti (Gupta et al, 2023) (Moreira et al, 2022) (Berkmans and Karthick, 2022) (Lu et al, 2020).…”

Section: Pendahuluanunclassified

Deteksi Transaksi Fraud Kartu Kredit Menggunakan Oversampling ADASYN dan Seleksi Fitur SVM-RFECV

Dharmana,

Gunadi,

Dewi

2024

JTIIK

View full text Add to dashboard Cite

Perkembangan kejahatan transaksi fraud kartu kredit memberikan dampak kerugian finansial bagi pemegang kartu. Pengembangan model deteksi transaksi fraud menggunakan machine learning telah dilakukan, namun memiliki beberapa tantangan meliputi ketidakseimbangan data serta dimensi dataset yang besar. Penelitian ini mengusulkan pendekatan pengembangan dengan seleksi fitur menggunakan SVM-RFECV dan metode oversampling dengan ADASYN. Pendekatan ini diharapkan mampu mengatasi permasalahan dimensi data serta ketidakseimbangan data yang terjadi. Seleksi fitur dengan SVM-RFECV menghasilkan variabel optimal pada rasio data latih 70% sejumlah 390 variabel, rasio data latih 80% sejumlah 400 variabel dan rasio data latih 90% sejumlah 390 variabel. Metode ADASYN telah memperbaiki ketidakseimbangan data dengan menghasilkan data sintetis berdasarkan rasio oversampling meliputi 100%, 50% dan 25%. Model yang menggunakan data hasil oversampling mengalami peningkatan kinerja AUC dan recall. Kinerja AUC tertinggi dihasilkan sejumlah 88,08% pada data latih 70%, oversampling 100% dan algoritma LGBM. Sedangkan, kinerja recall tertinggi sejumlah 83,08% dihasilkan saat menggunakan data latih 70%, oversampling 100% dengan algoritma AdaBoost. Berdasarkan pembahasan ini, maka dapat disimpulkan bahwa penggunaan oversampling dengan ADASYN dan seleksi fitur SVM-RFECV dapat dipertimbangkan untuk meningkatkan kinerja AUC dan recall.

show abstract

Section: Pendahuluanunclassified

Deteksi Transaksi Fraud Kartu Kredit Menggunakan Oversampling ADASYN dan Seleksi Fitur SVM-RFECV

Dharmana,

Gunadi,

Dewi

2024

JTIIK

View full text Add to dashboard Cite

show abstract

“…• Logistic Regression [8, 10-12, 22, 28, 29] • Support Vector Machines [21,22,27,29,30] • Neural Networks [1,3,5,13,18,26,27,31] • Decision Trees [6,7,11,18,22,28] • Random Forests [6-8, 11, 12, 15, 21, 22, 28] • Naive Bayes [11,[27][28][29] • K-Nearest Neighbors [11,22,29] • Isolation Forest [13,22,23] • Local Outlier Factor [10,13,23] Random Forests and Neural Networks generally produced good results, however, some researchers reported that Neural Networks took a long time to train. In general, the best suited algorithm depends on the properties of the data at hand, hence, the reason for many researchers taking the route of comparing the algorithms to determine the one that was most appropriate.…”

Section: Related Workmentioning

confidence: 99%

Framework for Credit Card Fraud Detection Using Benefit-Based Learning and Periodic Features

Sooklal

Hosein

2023

Preprint

View full text Add to dashboard Cite

Online credit card fraud is an ongoing problem and with the recent COVID-19 pandemic, there has been a surge of merchants moving their businesses online. It is therefore crucial to identify fraudulent activities before it causes loss to both the bank and its customers. Due to the dynamic nature of fraudsters as well as customer spending behavior, machine learning algorithms are appropriate for this task. However, credit card fraud data is typically imbalanced, favoring the positive class (legitimate transactions), causing traditional machine learning algorithms to err on the side of this majority class; since they consider equal costs and benefits for different decision outcomes when training. Nevertheless, it is more beneficial to correctly identify fraudulent transactions. Therefore, in this paper, we propose a technique for identifying credit card fraud that first accounts for customer spending patterns by aggregating transactions to creative new features based on periodic data. Then, we consider benefits and costs when training an XGBoost classifier in order to achieve maximum benefits. We also evaluate the performance of the classifier using benefits and costs. We demonstrate the effectiveness of our approach using data provided by a bank.

show abstract

“…For credit card fraud detection, a Decision tree and random forest are used [17]. The author has used public data as sample data to test the model's efficiency.…”

Section: Related Workmentioning

confidence: 99%

Detection of Credit Card Fraud using a Hybrid Ensemble Model

Saraf¹,

Phakatkar²

2022

IJACSA

View full text Add to dashboard Cite

The rising number of credit card frauds presents a significant challenge for the banking industry. Many businesses and financial institutions suffer huge losses because card users are reluctant to use their cards. A primary goal of fraud detection is to identify prior transaction patterns to detect future fraud. In this paper, a hybrid ensemble model is proposed to combine bagging and boosting techniques to distinguish between fraudulent and legitimate transactions. During the experimentation two datasets are used; the European credit card dataset and the credit card stimulation dataset which are highly imbalanced. The oversampling method is used to balance both datasets. To overcome the problem of unbalanced data oversampling method is used. The model is trained to predict output results by combining random forest with Adaboost. The proposed model provides 98.27 % area under curve score on the European credit cards dataset and the stimulation credit card dataset gives 99.3 % area under curve score.

show abstract

A Novel Approach for Credit Card Fraud Detection using Decision Tree and Random Forest Algorithms

Cited by 31 publications

References 11 publications

Deteksi Transaksi <i>Fraud </i>Kartu Kredit Menggunakan <i>Oversampling </i>ADASYN<i> </i>dan Seleksi Fitur SVM-RFECV

Deteksi Transaksi <i>Fraud </i>Kartu Kredit Menggunakan <i>Oversampling </i>ADASYN<i> </i>dan Seleksi Fitur SVM-RFECV

Framework for Credit Card Fraud Detection Using Benefit-Based Learning and Periodic Features

Detection of Credit Card Fraud using a Hybrid Ensemble Model

Contact Info

Product

Resources

About