A Review of Cryptocurrency Data Mining and Fraud Detection

DOI

10.2991/978-94-6239-701-9_78How to use a DOI?

Keywords

IIoT; Anomaly Detection; Traffic Analysis

Abstract

Anomaly detection in Industrial IoT (IIoT) is critical, yet current data-driven methods suffer from high false positives due to data imbalance, poor generalization, and the limited applicability of single models. To address these challenges, we propose a multi-stage framework for robust IIoT anomaly detection. Our system first employs a pre-processing module that uniquely supports both supervised and unsupervised learning by using K-Means clustering to generate pseudo-labels for unlabeled data, reducing the reliance on extensive manual labeling. Subsequently, an XGBoost-based module selects the most salient features. To enhance model input, a deep learning module then extracts advanced features: a Convolutional Neural Network (CNN) captures spatial patterns from raw packets, while a Long Short-Term Memory (LSTM) network models temporal correlations, with its output augmenting the feature set for a CART model. Finally, an optimally weighted ensemble of diverse classifiers—including Decision Tree, Random Forest, SVM, ANN, and Bayesian models—performs the final anomaly type classification. This integrated framework is designed to overcome the limitations of traditional methods by improving detection accuracy, reducing false positives, and enhancing generalization for dynamic IIoT environments.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Zejing Chen
PY  - 2026
DA  - 2026/07/30
TI  - A Review of Cryptocurrency Data Mining and Fraud Detection
BT  - Proceedings of the 2026 11th International Conference on Social Sciences and Economic Development (ICSSED 2026)
PB  - Atlantis Press
SP  - 754
EP  - 763
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6239-701-9_78
DO  - 10.2991/978-94-6239-701-9_78
ID  - Chen2026
ER  -