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
- Caleb Dow
- Bhavani Patangay
- Pritom Dutta
- Samuel Yeneneh
- Sucharitha Shivva
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