The Study and Models That Work
Academics published a research study that used machine learning to predict which cryptocurrency assets with at least 210 days of trading history would become "zombie" assets over the next 28 day period. Zombie assets are defined as assets that "have not been listed on an exchange for up to a month, even if not official withdrawn from the market." The timeframe used in the study was 2015 to the end of 2022, so it definitely covered a huge boom period in the cryptocurrency markets. Some machine learning models performed better than others... in this case, a Random Forest model scored the best (with an 84% accuracy rate), and it was closely followed by XGB "extreme gradient boost".... It is no surprise to see XGB on this list as it seems to excel at many prediction use cases.
Useful Predictive Features
The next big important question is: what sort of features or predictors were the models using to be able to determine such a high accuracy rate? According to the study, the minimum/maximum trading volumes and median returns from previous periods were the most predictive. "Simple" models, especially those with fewer features, were found to generally perform better than more complex models.
Unimportant Predictive Features
In this study, these categorical features did not increase predictive power of the model and did not show significance in this prediction... You will not likely be surprised at that result when you read what the predictors are, but definitely a very creative feature prediction set used by the research team.
What is the category of the cryptocurrency symbol?
Does the coin have a related Twitter (X) account?
Is the token mineable?
Bedowska-Sojka, Barbara and Wojcik, Piotr and Pele, Daniel Traian, Early Warning Systems for Cryptocurrency Markets: Predicting 'Zombie' Assets Using Machine Learning
Notice: Information contained herein is not and should not be construed as an offer, solicitation, or recommendation to buy or sell securities. The information has been obtained from sources we
believe to be reliable; however no guarantee is made or implied with respect to its accuracy, timeliness, or completeness. Author does not own the any crypto currency discussed. The information
and content are subject to change without notice. CryptoDataDownload and its affiliates do not provide investment, tax, legal or accounting advice.
This material has been prepared for informational purposes only and is the opinion of the author, and is not intended to provide, and should not be relied on for, investment, tax, legal,
accounting advice. You should consult your own investment, tax, legal and accounting advisors before engaging in any transaction. All content published by CryptoDataDownload is not an
endorsement whatsoever. CryptoDataDownload was not compensated to submit this article. Please also visit our Privacy policy; disclaimer; and terms and conditions page for further information.
THE PERFORMANCE OF TRADING SYSTEMS IS BASED ON THE USE OF COMPUTERIZED SYSTEM LOGIC. IT IS HYPOTHETICAL.
PLEASE NOTE THE FOLLOWING DISCLAIMER.
CFTC RULE 4.41: HYPOTHETICAL OR SIMULATED PERFORMANCE RESULTS HAVE CERTAIN LIMITATIONS. UNLIKE AN ACTUAL
PERFORMANCE RECORD, SIMULATED RESULTS DO NOT REPRESENT ACTUAL TRADING. ALSO, SINCE THE TRADES HAVE NOT BEEN
EXECUTED, THE RESULTS MAY HAVE UNDER-OR-OVER COMPENSATED FOR THE IMPACT, IF ANY, OF CERTAIN MARKET FACTORS,
SUCH AS LACK OF LIQUIDITY. SIMULATED TRADING PROGRAMS IN GENERAL ARE ALSO SUBJECT TO THE FACT THAT THEY ARE
DESIGNED WITH THE BENEFIT OF HINDSIGHT. NO REPRESENTATION IS BEING MADE THAT ANY ACCOUNT WILL OR IS LIKELY
TO ACHIEVE PROFIT OR LOSSES SIMILAR TO THOSE SHOWN. U.S. GOVERNMENT REQUIRED DISCLAIMER: COMMODITY FUTURES
TRADING COMMISSION. FUTURES AND OPTIONS TRADING HAS LARGE POTENTIAL REWARDS, BUT ALSO LARGE POTENTIAL RISK.
YOU MUST BE AWARE OF THE RISKS AND BE WILLING TO ACCEPT THEM IN ORDER TO INVEST IN THE FUTURES AND OPTIONS MARKETS.
DON’T TRADE WITH MONEY YOU CAN’T AFFORD TO LOSE. THIS IS NEITHER A SOLICITATION NOR AN OFFER TO BUY/SELL FUTURES
OR OPTIONS. NO REPRESENTATION IS BEING MADE THAT ANY ACCOUNT WILL OR IS LIKELY TO ACHIEVE PROFITS OR LOSSES
SIMILAR TO THOSE DISCUSSED ON THIS WEBSITE. THE PAST PERFORMANCE OF ANY TRADING SYSTEM OR METHODOLOGY IS NOT
NECESSARILY INDICATIVE OF FUTURE RESULTS.