Tensor time series change-point detection in cryptocurrency network data

2025-10-07

AI Summary

Cryptocurrency cross-platform trading networks exhibit covert, high-frequency fraud and market manipulation, posing significant challenges for regulatory oversight. Method: This paper proposes a tensor time-series-based change-point detection method. Its core innovation is a dynamic “network-of-networks” tensor model, which captures multi-platform transaction interdependencies via higher-order tensor decomposition. The method further integrates second-order cross-covariance analysis with a multi-scale detection strategy to robustly identify subtle structural changes. Contribution/Results: Compared to state-of-the-art approaches, the proposed method significantly improves detection accuracy and sensitivity for high-dimensional temporal network data. Extensive evaluation on real Ethereum transaction data and synthetic benchmarks demonstrates its effectiveness: detected change points precisely align with topological transitions induced by cross-platform collusive manipulation. The framework delivers an interpretable, scalable paradigm for regtech applications, enabling timely, evidence-based regulatory intervention.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Matrix & Tensor Methods
• Natural Language Processing: Machine Translation, Multilinguality, Cross-Lingual NLP

Application Category

• Economics, Online Markets and Human Computation: Economic aspects of blockchain and cryptocurrencies
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Financial fraud has been growing exponentially in recent years. The rise of cryptocurrencies as an investment asset has simultaneously seen a parallel growth in cryptocurrency scams. To detect possible cryptocurrency fraud, and in particular market manipulation, previous research focused on the detection of changes in the network of trades; however, market manipulators are now trading across multiple cryptocurrency platforms, making their detection more difficult. Hence, it is important to consider the identification of changes across several trading networks or a `network of networks'over time. To this end, in this article, we propose a new change-point detection method in the network structure of tensor-variate data. This new method, labeled TenSeg, first employs a tensor decomposition, and second detects multiple change-points in the second-order (cross-covariance or network) structure of the decomposed data. It allows for change-point detection in the presence of frequent changes of possibly small magnitudes and is computationally fast. We apply our method to several simulated datasets and to a cryptocurrency dataset, which consists of network tensor-variate data from the Ethereum blockchain. We demonstrate that our approach substantially outperforms other state-of-the-art change-point techniques, and the detected change-points in the Ethereum data set coincide with changes across several trading networks or a `network of networks'over time. Finally, all the relevant extsf{R} code implementing the method in the article are available on https://github.com/Anastasiou-Andreas/TenSeg.

Problem

• Detecting change-points in cryptocurrency trading network structures
• Identifying market manipulation across multiple cryptocurrency platforms
• Developing tensor-based method for network of networks analysis

Innovation

• Tensor decomposition for network structure analysis
• Multiple change-point detection in cross-covariance structure
• Fast computation for frequent small-magnitude network changes