International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
Volume 187 - Issue 11 |
Published: June 2025 |
Authors: Anjali, Anshul Jauhari, Mehwish Shahnawaz, Mohammad Tabish, Pushpendra Dwivedi |
![]() |
Anjali, Anshul Jauhari, Mehwish Shahnawaz, Mohammad Tabish, Pushpendra Dwivedi . Transaction Fraud Detection using Amazon Fraud Detector and AWS Cloud Services. International Journal of Computer Applications. 187, 11 (June 2025), 10-12. DOI=10.5120/ijca2025925069
@article{ 10.5120/ijca2025925069, author = { Anjali,Anshul Jauhari,Mehwish Shahnawaz,Mohammad Tabish,Pushpendra Dwivedi }, title = { Transaction Fraud Detection using Amazon Fraud Detector and AWS Cloud Services }, journal = { International Journal of Computer Applications }, year = { 2025 }, volume = { 187 }, number = { 11 }, pages = { 10-12 }, doi = { 10.5120/ijca2025925069 }, publisher = { Foundation of Computer Science (FCS), NY, USA } }
%0 Journal Article %D 2025 %A Anjali %A Anshul Jauhari %A Mehwish Shahnawaz %A Mohammad Tabish %A Pushpendra Dwivedi %T Transaction Fraud Detection using Amazon Fraud Detector and AWS Cloud Services%T %J International Journal of Computer Applications %V 187 %N 11 %P 10-12 %R 10.5120/ijca2025925069 %I Foundation of Computer Science (FCS), NY, USA
This work aims to come up with a machine learning model that will be able to recognize fraud in online transactions with Amazon Web Services (AWS) tools. Amazon Fraud Detector through the use of this tool was able to be fed a wide range of transaction data that were not only genuine but also had examples of fraud. The work required data collection from an Amazon S3, event types and variables setting up, and model training to discover suspicious patterns. Once the training is over, the model can be tested using information it hasn't been exposed to and be given a variety of results that include fraud scores and classification decisions (fraud or legitimate). Cloud services from AWS, like integrated API, IAM, and CloudWatch, make the system operate in real-time too. The findings demonstrate that it is possible to build a full-fledged fraud detection system without the need for extensive knowledge in machine learning.