Comparative Analysis of Back-propagation Neural Network and K-Means Clustering Algorithm in Fraud Detection in Online Credit Card Transactions
The ubiquitous nature of the internet had been a major driving force of the digital transformation in our world today. It has necessarily become the main medium for conducting electronic commerce (e-commerce) and online transactions. With this development, various means of possible payment methods...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Fountain University Osogbo
2019-06-01
|
| Series: | Fountain Journal of Natural and Applied Sciences (FUJNAS) |
| Online Access: | https://fountainjournals.com/index.php/FUJNAS/article/view/315 |
| _version_ | 1797665692759097344 |
|---|---|
| author | B.A. Abdulsalami A. A. Kolawole M.A. Ogunrinde M. Lawal R.A. Azeez A.Z. Afolabi |
| author_facet | B.A. Abdulsalami A. A. Kolawole M.A. Ogunrinde M. Lawal R.A. Azeez A.Z. Afolabi |
| author_sort | B.A. Abdulsalami |
| collection | DOAJ |
| description |
The ubiquitous nature of the internet had been a major driving force of the digital transformation in our world today. It has necessarily become the main medium for conducting electronic commerce (e-commerce) and online transactions. With this development, various means of possible payment methods have also emerged, such as electronic cash/ cheques, debit/credit cards, and electronic wallets. However, debit/credit cards are by far the most common payment methods employed. As a result, different credit card fraud activities have rapidly increased all over the world and are still evolving. This menace has drawn a lot of research interest and a number of techniques, with special emphasis on Data Mining, Expert System and Machine Learning (ML), as a means of identifying fraudulent behaviors. This paper examines and investigates two ML algorithms trained on public online credit card datasets, to analyze and identify fraudulent transactions. The BPNN and the K-means clustering ML algorithms were designed and implemented using Python Programming Languages. It was determined that the BPNN has a much higher accuracy of 93.1% as compared to the K-means which has an accuracy of 79.9%. Other metrics used to evaluate their performance also shows that the BPNN algorithm outperformed K-means algorithm, while the low prediction time of K-means gave it an advantage over the BPNN.
Keywords: Credit card, Fraud detection, Back-Propagation neural network, Clustering algorithm, Machine learning, Security.
|
| first_indexed | 2024-03-11T19:48:45Z |
| format | Article |
| id | doaj.art-b3bf24f113b0415f9c3d5ccf6ea9c57f |
| institution | Directory Open Access Journal |
| issn | 2350-1863 2354-337X |
| language | English |
| last_indexed | 2024-03-11T19:48:45Z |
| publishDate | 2019-06-01 |
| publisher | Fountain University Osogbo |
| record_format | Article |
| series | Fountain Journal of Natural and Applied Sciences (FUJNAS) |
| spelling | doaj.art-b3bf24f113b0415f9c3d5ccf6ea9c57f2023-10-05T16:55:00ZengFountain University OsogboFountain Journal of Natural and Applied Sciences (FUJNAS)2350-18632354-337X2019-06-0181Comparative Analysis of Back-propagation Neural Network and K-Means Clustering Algorithm in Fraud Detection in Online Credit Card TransactionsB.A. Abdulsalami0A. A. Kolawole1M.A. Ogunrinde2M. Lawal3R.A. Azeez4A.Z. Afolabi5Department of Mathematical and Computer Sciences, Fountain University, Osogbo, NigeriaDepartment of Mathematical and Computer Sciences, Fountain University, Osogbo, NigeriaDepartment of Mathematical and Computer Sciences, Fountain University, Osogbo, NigeriaDepartment of Mathematical and Computer Sciences, Fountain University, Osogbo, NigeriaDepartment of Mathematical and Computer Sciences, Fountain University, Osogbo, NigeriaDepartment of Mathematical and Computer Sciences, Fountain University, Osogbo, Nigeria The ubiquitous nature of the internet had been a major driving force of the digital transformation in our world today. It has necessarily become the main medium for conducting electronic commerce (e-commerce) and online transactions. With this development, various means of possible payment methods have also emerged, such as electronic cash/ cheques, debit/credit cards, and electronic wallets. However, debit/credit cards are by far the most common payment methods employed. As a result, different credit card fraud activities have rapidly increased all over the world and are still evolving. This menace has drawn a lot of research interest and a number of techniques, with special emphasis on Data Mining, Expert System and Machine Learning (ML), as a means of identifying fraudulent behaviors. This paper examines and investigates two ML algorithms trained on public online credit card datasets, to analyze and identify fraudulent transactions. The BPNN and the K-means clustering ML algorithms were designed and implemented using Python Programming Languages. It was determined that the BPNN has a much higher accuracy of 93.1% as compared to the K-means which has an accuracy of 79.9%. Other metrics used to evaluate their performance also shows that the BPNN algorithm outperformed K-means algorithm, while the low prediction time of K-means gave it an advantage over the BPNN. Keywords: Credit card, Fraud detection, Back-Propagation neural network, Clustering algorithm, Machine learning, Security. https://fountainjournals.com/index.php/FUJNAS/article/view/315 |
| spellingShingle | B.A. Abdulsalami A. A. Kolawole M.A. Ogunrinde M. Lawal R.A. Azeez A.Z. Afolabi Comparative Analysis of Back-propagation Neural Network and K-Means Clustering Algorithm in Fraud Detection in Online Credit Card Transactions Fountain Journal of Natural and Applied Sciences (FUJNAS) |
| title | Comparative Analysis of Back-propagation Neural Network and K-Means Clustering Algorithm in Fraud Detection in Online Credit Card Transactions |
| title_full | Comparative Analysis of Back-propagation Neural Network and K-Means Clustering Algorithm in Fraud Detection in Online Credit Card Transactions |
| title_fullStr | Comparative Analysis of Back-propagation Neural Network and K-Means Clustering Algorithm in Fraud Detection in Online Credit Card Transactions |
| title_full_unstemmed | Comparative Analysis of Back-propagation Neural Network and K-Means Clustering Algorithm in Fraud Detection in Online Credit Card Transactions |
| title_short | Comparative Analysis of Back-propagation Neural Network and K-Means Clustering Algorithm in Fraud Detection in Online Credit Card Transactions |
| title_sort | comparative analysis of back propagation neural network and k means clustering algorithm in fraud detection in online credit card transactions |
| url | https://fountainjournals.com/index.php/FUJNAS/article/view/315 |
| work_keys_str_mv | AT baabdulsalami comparativeanalysisofbackpropagationneuralnetworkandkmeansclusteringalgorithminfrauddetectioninonlinecreditcardtransactions AT aakolawole comparativeanalysisofbackpropagationneuralnetworkandkmeansclusteringalgorithminfrauddetectioninonlinecreditcardtransactions AT maogunrinde comparativeanalysisofbackpropagationneuralnetworkandkmeansclusteringalgorithminfrauddetectioninonlinecreditcardtransactions AT mlawal comparativeanalysisofbackpropagationneuralnetworkandkmeansclusteringalgorithminfrauddetectioninonlinecreditcardtransactions AT raazeez comparativeanalysisofbackpropagationneuralnetworkandkmeansclusteringalgorithminfrauddetectioninonlinecreditcardtransactions AT azafolabi comparativeanalysisofbackpropagationneuralnetworkandkmeansclusteringalgorithminfrauddetectioninonlinecreditcardtransactions |