Big Data-Driven Distributed Machine Learning for Scalable Credit Card Fraud Detection Using PySpark, XGBoost, and CatBoost DOI Open Access
Leonidas Theodorakopoulos, Alexandra Theodoropoulou, Anastasios Tsimakis

et al.

Electronics, Journal Year: 2025, Volume and Issue: 14(9), P. 1754 - 1754

Published: April 25, 2025

This study presents an optimization for a distributed machine learning framework to achieve credit card fraud detection scalability. Due the growth in fraudulent activities, this research implements PySpark-based processing of large-scale transaction datasets, integrating advanced models: Logistic Regression, Decision Trees, Random Forests, XGBoost, and CatBoost. These have been evaluated terms scalability, accuracy, handling imbalanced datasets. Key findings: Among most promising models complex data, XGBoost CatBoost promise close-to-ideal accuracy rates detection. PySpark will be instrumental scaling these systems enable them perform processing, real-time analysis, adaptive learning. further discusses challenges like overfitting, data access, implementation with potential solutions such as ensemble methods, intelligent sampling, graph-based approaches. Future directions are underlined by deploying frameworks live environments, leveraging continuous mechanisms, anomaly techniques handle evolving patterns. The present demonstrates importance developing robust, scalable, efficient systems, considering their significant impact on financial security overall ecosystem.

Language: Английский

Impact of Information and Communication Technologies on Democratic Processes and Citizen Participation DOI Creative Commons
George Asimakopoulos, Hera Antonopoulou, Konstantinos C. Giotopoulos

et al.

Societies, Journal Year: 2025, Volume and Issue: 15(2), P. 40 - 40

Published: Feb. 18, 2025

Background: This systematic review will address the influence of Information and Communication Technologies (ICTs) on democratic processes citizens’ participation, which is enabled by such tools as social media, e-voting systems, e-government initiatives, e-participation platforms. Methods: Based an in-depth analysis 46 peer-reviewed articles published between 1999 2024, this emphasizes how ICTs have improved engagement quality, efficiency, transparency, but highlights key challenges research gaps. Results: From angle, ICT great potential to nurture civic good governance through transparency. Challenges persist with ethical implications surveillance technologies, security concerns about digital voting widening divide disproportionately affecting marginalized populations. The current regulatory framework dealing privacy misinformation issues relatively weak, there also a lack understanding ICTs’ long-term effects governance. Conclusions: underlines duality roles played both enabler challenge processes. It calls for measures protect privacy, fight disinformation, reduce divide. Future in area should focus they can be equitably efficiently integrated into strategies aimed at maximizing benefits while minimizing risks.

Language: Английский

Citations

2
Blockchain Applications in the Military Domain: A Systematic Review DOI Creative Commons
Nikos Kostopoulos, Yannis C. Stamatiou, Constantinos Halkiopoulos

et al.

Technologies, Journal Year: 2025, Volume and Issue: 13(1), P. 23 - 23

Published: Jan. 6, 2025

Background: Blockchain technology can transform military operations, increasing security and transparency gaining efficiency. It addresses many problems related to data security, privacy, communication, supply chain management. The most researched aspects are its integration with emerging technologies, such as artificial intelligence, the IoT, application in uncrewed aerial vehicles, secure communications. Methods: A systematic review of 43 peer-reviewed articles was performed discover applications blockchain defense. Key areas analyzed include role securing communications, fostering transparency, promoting real-time sharing, using smart contracts for maintenance Challenges were assessed, including scalability, interoperability, legacy system, alongside possible solutions, sharding optimized consensus mechanisms. Results: In case blockchain, great potential benefits shown enhancing immutable record keeping, IoT AI. Smart resource allocation reduced procedures. However, challenges remain, high energy requirements. Proposed like hybrid architecture, show promise address these issues. Conclusions: is set revolutionize efficiency military. Its enormous, but it must overcome Further research strategic adoption will thus allow become one cornerstones future operations.

Language: Английский

Citations

1
Real-Time Analysis of Industrial Data Using the Unsupervised Hierarchical Density-Based Spatial Clustering of Applications with Noise Method in Monitoring the Welding Process in a Robotic Cell DOI Creative Commons
Tomasz Bƚachowicz,

Jacek Wylezek,

Zbigniew Sokol

et al.

Information, Journal Year: 2025, Volume and Issue: 16(2), P. 79 - 79

Published: Jan. 22, 2025

The application of modern machine learning methods in industrial settings is a relatively new challenge and remains the early stages development. Current computational power enables processing vast numbers production parameters real time. This article presents practical analysis welding process robotic cell using unsupervised HDBSCAN algorithm, highlighting its advantages over classical k-means algorithm. paper also addresses problem predicting monitoring undesirable situations proposes use real-time graphical representation noisy data as particularly effective solution for managing such issues.

Language: Английский

Citations

0
Big Data-Driven Distributed Machine Learning for Scalable Credit Card Fraud Detection Using PySpark, XGBoost, and CatBoost DOI Open Access
Leonidas Theodorakopoulos, Alexandra Theodoropoulou, Anastasios Tsimakis

et al.

Electronics, Journal Year: 2025, Volume and Issue: 14(9), P. 1754 - 1754

Published: April 25, 2025

This study presents an optimization for a distributed machine learning framework to achieve credit card fraud detection scalability. Due the growth in fraudulent activities, this research implements PySpark-based processing of large-scale transaction datasets, integrating advanced models: Logistic Regression, Decision Trees, Random Forests, XGBoost, and CatBoost. These have been evaluated terms scalability, accuracy, handling imbalanced datasets. Key findings: Among most promising models complex data, XGBoost CatBoost promise close-to-ideal accuracy rates detection. PySpark will be instrumental scaling these systems enable them perform processing, real-time analysis, adaptive learning. further discusses challenges like overfitting, data access, implementation with potential solutions such as ensemble methods, intelligent sampling, graph-based approaches. Future directions are underlined by deploying frameworks live environments, leveraging continuous mechanisms, anomaly techniques handle evolving patterns. The present demonstrates importance developing robust, scalable, efficient systems, considering their significant impact on financial security overall ecosystem.

Language: Английский

Citations

0