Threshold-Based Detection of Crypto Pump-and-Dump Events

Summary

This document describes an unsupervised method for identifying suspected pump-and-dump events among tokens traded on Poloniex. It combines price and volume thresholds with exponentially weighted moving averages and volatility measures. The thresholds are tailored to observed trading patterns so that the detector can account for assets with low liquidity or long periods of inactivity, where ordinary anomaly methods may interpret small bursts of activity as meaningful events.

The stated goal is to separate substantial coordinated-looking moves from minor fluctuations while limiting false alarms. The description claims the approach balances detection and noise reduction, but supplies no dataset dates, threshold calibration procedure, measured precision or recall, or comparison results. A detection should therefore be understood as a screening signal rather than proof of manipulation. Its reported scope is a single exchange platform, so effectiveness on other venues or under different trading conditions is not established here.

Key ideas

• The method screens token price and volume activity for suspected pump-and-dump events.
• It combines tailored thresholds with exponentially weighted averages and volatility measures.
• Thresholds are adapted to account for thinly traded tokens and prolonged inactivity.
• The intended benefit is fewer alerts from insignificant volume spikes.
• The description provides no quantitative validation or evidence that an alert proves manipulation.

Tags

# Detecting Crypto Pump-and-Dump Schemes: A Thresholding-Based Approach to Handling Market Noise


# Detecting Crypto Pump-and-Dump Schemes: A Thresholding-Based Approach to Handling Market Noise









We propose a simple yet robust unsupervised model to detect pump-and-dump events on tokens listed on the Poloniex Exchange platform. By combining threshold-based criteria with exponentially weighted moving averages (EWMA) and volatility measures, our approach effectively distinguishes genuine anomalies from minor trading fluctuations, even for tokens with low liquidity and prolonged inactivity. These characteristics present a unique challenge, as standard anomaly-detection methods often over-flag negligible volume spikes. Our framework overcomes this issue by tailoring both price and volume thresholds to the specific trading patterns observed, resulting in a model that balances high true-positive detection with minimal noise.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.