Empirical Patterns and Prediction of Cryptocurrency Pump-and-Dump Events

Summary

This study examines coordinated cryptocurrency pump-and-dump activity, including a case study and an investigation of events organized through Telegram channels over a defined period. It looks for market patterns associated with these schemes and builds a model to estimate which listed coins are likely to be pumped before an event. The authors frame the work as both an empirical analysis of manipulated trading and an application of machine learning to detection.

The paper reports that the model has high precision and robustness, and tests a simple trading strategy based on its predictions. The reported empirical exercise found returns as high as 60% on small retail investments over roughly two and a half months. That figure is specific to the study's sample and setup; the abstract does not describe transaction costs, liquidity constraints, risk-adjusted performance, or out-of-sample validation details. The findings are best treated as a proof of concept, not a guarantee that the strategy can be reproduced or that trading around suspected manipulation is safe.

Key ideas

• The study analyzes cryptocurrency pump-and-dump events organized in Telegram channels.
• It investigates market patterns associated with coordinated pump activity.
• A machine learning model estimates the likelihood that a listed coin will be pumped.
• The authors report testing a trading strategy based on the model's predictions.
• Reported returns are tied to the study's historical sample and do not establish future performance.

Tags

# The Anatomy of a Cryptocurrency Pump-and-Dump Scheme


# The Anatomy of a Cryptocurrency Pump-and-Dump Scheme









While pump-and-dump schemes have attracted the attention of cryptocurrency observers and regulators alike, this paper represents the first detailed empirical query of pump-and-dump activities in cryptocurrency markets. We present a case study of a recent pump-and-dump event, investigate 412 pump-and-dump activities organized in Telegram channels from June 17, 2018 to February 26, 2019, and discover patterns in crypto-markets associated with pump-and-dump schemes. We then build a model that predicts the pump likelihood of all coins listed in a crypto-exchange prior to a pump. The model exhibits high precision as well as robustness, and can be used to create a simple, yet very effective trading strategy, which we empirically demonstrate can generate a return as high as 60% on small retail investments within a span of two and half months. The study provides a proof of concept for strategic crypto-trading and sheds light on the application of machine learning for crime detection.

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.