Researchers Say Machine Learning Can Predict Crypto Pump and Dumps
Jiahua Xu and Benjamin Livshits, researchers at Imperial College London, have developed a machine learning algorithm to predict when pump-and-dump schemes are about to occur in an effort to develop methods to subvert or prevent them.
In a report recently published in arXiv, Xu and Livshits identified and reviewed 237 pump-and-dump events that took place between July 21 and November 18, many of which leveraged thousand-person groups on the popular messaging platform Telegram.
“The study reveals that pump-and-dump organizers can easily use their insider information to take extra gain at the sacrifice of fellow pumpers,” stated Xu and Livshits.
In total, Xu and Livshits found that there are two pump-and-dump scams every day, which generate roughly $7 million worth of trading volume each month, relatively small amounts in the grand scheme of things.
Leveraging this data, Xu and Livshits produced a machine learning algorithm that pattern recognizes pump-and-dump schemes before they happen.
“We then build a model that predicts the pump likelihood of a given coin 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 80% within a span of only three weeks,” reads the analysis.
This study sheds a slightly different light on the matter compared to a recent analysis conducted by The Wall Street Journal that showed that dozens of pump-and-dump trading groups have routinely manipulated the prices of cryptocurrencies on large online exchanges to an amount of at least $825 million in the past six months.
These activities, according to the report, have been directly responsible for the loss of hundreds of millions of dollars in counterparty trades.
Disclaimer: This article’s author has cryptocurrency holdings that can be tracked here. This article is for informational purposes only and should not be taken as investment advice. Always conduct your own due diligence before making investments.