Penerapan Deep Learning dalam Deteksi Penipuan Transaksi Keuangan Secara Elektronik

Zamachsari, Faried; Puspitasari, Niken

doi:10.29207/resti.v5i2.2952

Cited by 4 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this chapter, we will discuss the results of research conducted using the Anaconda Navigator Python distribution package application analysis tool from Continuum Analytics. The data will be processed to predict the achievement of using the accuracy of each proposed algorithm performance by testing the credit card dataset [13]. The dataset used is data from Kaggle "Credit Card" which has 429 frauds from 284,807 transactions.…”

Section: Resultsmentioning

confidence: 99%

Fraud Detection Using Random Forest Classifier, Logistic Regression, and Gradient Boosting Classifier Algorithms on Credit Cards

2022

View full text Add to dashboard Cite

The following credit card records were used in this study of 284.807 transactions made by credit card holders in Europe for two days from the Kaggle dataset. This is a very poor data set, having 492 transactions, an imbalance of only 0.172% of the 284.807 transactions. The purpose of this study is to obtain the best model and then simulate it by electronically detecting unauthorized financial transactions in bank payment systems. The dataset for this study is unbalanced class data with 99.80% for the major class and 0.2% for the minor class. This type of class-imbalanced data problem is solved by applying method a combination of minority oversampling techniques using Synthetic Minority Oversampling Technique (SMOTE). To determine the most appropriate and accurate classification in solving class balance problems, comparisons were made with the Random Forest Classifier (RFC), Logistic Regression (LGR), and Gradient Boosting Classifier (GBC) algorithms. The test results in this study are the Random Forest Classifier (RFC) algorithm is better than other algorithms because it has the highest accuracy the percentage of data-train is 100% and data-test is 99.99% and the evaluation of the AUC score as a result of algorithm testing is 0.9999.

show abstract

Section: Resultsmentioning

confidence: 99%

Fraud Detection Using Random Forest Classifier, Logistic Regression, and Gradient Boosting Classifier Algorithms on Credit Cards

2022

View full text Add to dashboard Cite

show abstract

“…Research [8] uses the SVM method, but the data used is only 100 data, so the accuracy level cannot be obtained properly. Similar research on fraud detection was also conducted by [9] using the application of deep learning. By using SMOTE this research can improve accuracy and precision quite significantly.…”

Section: Customermentioning

confidence: 93%

Fraud Detection in Sales of Distribution Companies Using Machine Learning

Suhanjoyo,

Toba,

Suteja

2023

JuTISI

View full text Add to dashboard Cite

The sales department of a distribution company is one of the places where fraud often occurs. This fraud occurs in various ways and causes massive losses for the company. These frauds have certain patterns. The patterns that occur in these practices are studied by the company's internal auditor experts. The experience of these experts is processed into a system called the Expert System. The support of a technology-based tool is needed in order to detect sales fraud early. The purpose of this research is to be able to provide benefits for companies with early detection of fraud in the sales department. At the time this research was conducted, researchers had not found similar research with the same object. In this research, a comparison of various machine learning algorithm models will be carried out with the aim of knowing whether using machine learning technology can help detect fraud with a high accuracy value. The algorithm method used is supervised learning method. The algorithm models to be compared are Decision Tree, K-Nearest Neighbor, Random Forest, SVM and Logistic Regression. It is expected that by using machine learning technology, fraud can be detected early, so that the level of loss and risk of sales can be minimized.

show abstract

“…Tujuan penelitian ini adalah untuk menemukan model yang paling cocok untuk kemudian diterapkan ke dalam sistem pembayaran perbankan dengan tujuan mendeteksi penipuan transaksi keuangan secara elektronik dan mencegah penipuan yang akan merugikan perbankan dan nasabah [4].…”

Section: Pendahuluanunclassified

Pengembangan Aplikasi Bank Account Fraud Detection Dengan Menggunakan Algoritma Xgboost

Haris Prayoga,

Voutama

2024

jati

View full text Add to dashboard Cite

Penelitian ini menyelidiki pengembangan aplikasi "Bank account fraud detection" yang menggunakan algoritma XGBoost untuk menemukan penipuan dalam transaksi rekening bank. Pendahuluan membahas bagaimana teknologi informasi dan komunikasi (TIK) sangat penting bagi kehidupan manusia, khususnya di sektor keuangan. Kejahatan siber, yang mencakup skimming dan social engineering dalam industri jasa keuangan, adalah masalah utama. Tujuan penelitian adalah menciptakan model yang paling efektif untuk mendeteksi penipuan transaksi keuangan yang dilakukan secara elektronik. Proses pengumpulan data, eksplorasi data, modeling dengan algoritma XGBoost, evaluasi model, dan deployment aplikasi adalah bagian dari metodologi penelitian. Hasil penelitian menunjukkan bahwa XGBoost Classifier memiliki akurasi mendeteksi penipuan tertinggi dengan 95.67%. Dengan bantuan aplikasi, manajer bank dapat dengan cepat menemukan transaksi mencurigakan dan mengambil tindakan pencegahan, meningkatkan keamanan rekening bank dan melindungi data nasabah

show abstract

Penerapan Deep Learning dalam Deteksi Penipuan Transaksi Keuangan Secara Elektronik

Cited by 4 publications

References 18 publications

Fraud Detection Using Random Forest Classifier, Logistic Regression, and Gradient Boosting Classifier Algorithms on Credit Cards

Fraud Detection Using Random Forest Classifier, Logistic Regression, and Gradient Boosting Classifier Algorithms on Credit Cards

Fraud Detection in Sales of Distribution Companies Using Machine Learning

Pengembangan Aplikasi Bank Account Fraud Detection Dengan Menggunakan Algoritma Xgboost

Contact Info

Product

Resources

About