1313-GC SparkGuard: A Big Data Pipeline for Credit Card Fraud Detection

Fraud poses a significant threat to both organizations and individuals, making effective detection critical for protecting society. In this project, we evaluate various machine learning approaches to credit card fraud detection- including support vector machines (SVM), XGBoost, random forest, neural networks, and a voting ensemble approach aggregating multiple models. To overcome single-node memory and processing bottlenecks on highly imbalanced data, we deploy a Big Data pipeline. For each approach, we implement a system to evaluate performance using accuracy, precision, recall, F1 score, and receiver operating characteristics (ROC). Comparing these metrics allows us to assess each approach in identifying fraudulent activity and determine the optimal solution.

Authors

Publication Details

Journal
DigitalCommons - Kennesaw State University (Kennesaw State University)
Published
2026-11-20
Primary Topic
Imbalanced Data Classification Techniques
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

1313-GC SparkGuard: A Big Data Pipeline for Credit Card Fraud Detection

Caleb Dow, Bhavani Patangay, Pritom Dutta, Samuel Yeneneh et al.
DigitalCommons - Kennesaw State University (Kennesaw State University)
Imbalanced Data Classification Techniques
article

1313-GC SparkGuard: A Big Data Pipeline for Credit Card Fraud Detection

Caleb Dow, Bhavani Patangay, Pritom Dutta, Samuel Yeneneh, Sucharitha Shivva
article en

Abstract

Fraud poses a significant threat to both organizations and individuals, making effective detection critical for protecting society. In this project, we evaluate various machine learning approaches to credit card fraud detection- including support vector machines (SVM), XGBoost, random forest, neural networks, and a voting ensemble approach aggregating multiple models. To overcome single-node memory and processing bottlenecks on highly imbalanced data, we deploy a Big Data pipeline. For each approach, we implement a system to evaluate performance using accuracy, precision, recall, F1 score, and receiver operating characteristics (ROC). Comparing these metrics allows us to assess each approach in identifying fraudulent activity and determine the optimal solution.

DigitalCommons - Kennesaw State University (Kennesaw State University)
Imbalanced Data Classification Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon