Cryptocurrency markets often face manipulation through prevalent pump-and-dump (P&D) schemes, where self-organized Telegram groups, some exceeding two million members, artificially inflate target cryptocurrency prices. These groups sell premium access to inside information, worsening information asymmetry and financial risks for subscribers and all investors. This paper presents a real-time prediction pipeline to forecast target coins and alert investors to possible P&D schemes. In a Poloniex case study, the model accurately identified the target coin among the top five from 50 random coins in 24 out of 43 (55.81%) P&D events. The pipeline uses advanced natural language processing (NLP) to classify Telegram messages, identifying 2,079 past pump events and detecting new ones in real-time.
@article{arxiv.2412.18848,
title = {Machine Learning-Based Detection of Pump-and-Dump Schemes in Real-Time},
author = {Manuel Bolz and Kevin Brundler and Liam Kane and Panagiotis Patsias and Liam Tessendorf and Krzysztof Gogol and Taehoon Kim and Claudio Tessone},
journal= {arXiv preprint arXiv:2412.18848},
year = {2025}
}