Related Experiment Videos
Detecting Unusual Trading Patterns on Cryptocurrency Exchanges by Means of Complexity Measures
Jakub Zwydak1, Marcin Wątorek1, Jarosław Kwapień2
1Faculty of Computer Science and Mathematics, Cracow University of Technology, ul. Warszawska 24, 31-155 Kraków, Poland.
Entropy (Basel, Switzerland)
|July 28, 2026
Summary
This study introduces a new framework to detect artificial cryptocurrency trading. It found unusual patterns on Bitget, suggesting potential market manipulation through increased transaction counts.
Area of Science:
- Financial markets
- Cryptocurrency trading
- Market manipulation detection
Background:
- Artificial transaction generation poses a significant threat to cryptocurrency exchange integrity.
- Such activity can distort liquidity and obscure market transparency.
Purpose of the Study:
- To develop and apply a diagnostic framework for identifying unusual trading patterns indicative of market manipulation.
- To analyze high-frequency trade data using complexity and statistical structure measures.
Main Methods:
- Analysis of log-returns, trading volume, and transaction counts.
- Utilized tail distributions, autocorrelation functions, multifractal characteristics, approximate entropy, and detrended cross-correlations.
- Applied methodology to BTC, ETH, and XRP data from major exchanges (Binance, Bitget, KuCoin, Kraken) between April 1 and June 30, 2025.
Main Results:
- A distinct anomaly was identified on Bitget for BTC and ETH post-mid-May 2025.
- Characterized by a sharp rise in transaction counts without proportional increases in volume or return volatility.
- Observed features include low-volume trades, weakened autocorrelations, reduced multifractality, and higher short-pattern irregularity.
Conclusions:
- Complexity-based indicators effectively detect exchange-specific trading anomalies missed by price-based measures.
- The identified anomaly suggests artificially inflated transaction counts, potentially indicating market manipulation.
- While not direct proof of wash trading, the findings highlight the utility of advanced analytical techniques for market surveillance.
Related Concept Videos
01:16Unusual Results
Unusual results are those that have a very low chance of occurring. Unusual results can be identified using probabilities and the range rule of thumb. In problems involving probability, unusual results can be observed in 2 instances – an unusually high number of successes or an unusually low number of successes.
According to the range rule of thumb, any value above or below two standard deviations, 2σ from the mean, μ is considered unusual.
Maximum unusual value = μ + 2σ
Minimum unusual value...
According to the range rule of thumb, any value above or below two standard deviations, 2σ from the mean, μ is considered unusual.
Maximum unusual value = μ + 2σ
Minimum unusual value...
01:02Quantifying and Rejecting Outliers: The Grubbs Test
Sometimes, a data set can have a recorded numerical observation that greatly deviates from the rest of the data. Assuming that the data is normally distributed, a statistical method called the Grubbs test can be used to determine whether the observation is truly an outlier. To perform a two-tailed Grubbs test, first, calculate the absolute difference between the outlier and the mean. Then, calculate the ratio between this difference and the standard deviation of the sample. This number is...