Skip to content
All library documents

Using On-Chain Data to Classify Cryptocurrency Risk and Price Factors

Article arXiv papers · Author: Abdulrezzak Zekiye et al.
Read the original

Summary

The study examines whether cryptocurrency on-chain measures can help explain prices and distinguish risky assets. It analyzes historical data, measures correlations between price and other parameters, groups cryptocurrencies using clustering, and applies classification algorithms to label assets as risky or not. The clusters are intended to let investors compare a coin with others that have similar on-chain profiles.

The reported data show that 39% of the cryptocurrencies disappeared, while 10% lasted more than 1,000 days. Price has a significant negative correlation with maximum and total supply and a weak positive correlation with 24-hour trading volume. Clustering produces five groups, and the best reported risk-classification F1 score is 76% using K-nearest neighbors. These are historical associations and classification results, not evidence that the features cause price changes or guarantee future risk detection. The excerpt does not describe the sample construction, validation design, or performance across changing market conditions.

Key ideas

  • The analysis uses historical on-chain measures to study cryptocurrency prices and risk classification.
  • Maximum and total supply are reported to have significant negative correlations with price.
  • Trading volume over 24 hours has a weak positive correlation with price.
  • Clustering places cryptocurrencies into five groups based on on-chain parameters.
  • K-nearest neighbors achieves the best stated risk-classification F1 score of 76%.

Tags

CryptoOn-chain dataMachine learningStatisticsRisk management
Full text
# AI-Assisted Investigation of On-Chain Parameters: Risky Cryptocurrencies and Price Factors


# AI-Assisted Investigation of On-Chain Parameters: Risky Cryptocurrencies and Price Factors









Cryptocurrencies have become a popular and widely researched topic of interest in recent years for investors and scholars. In order to make informed investment decisions, it is essential to comprehend the factors that impact cryptocurrency prices and to identify risky cryptocurrencies. This paper focuses on analyzing historical data and using artificial intelligence algorithms on on-chain parameters to identify the factors affecting a cryptocurrency's price and to find risky cryptocurrencies. We conducted an analysis of historical cryptocurrencies' on-chain data and measured the correlation between the price and other parameters. In addition, we used clustering and classification in order to get a better understanding of a cryptocurrency and classify it as risky or not. The analysis revealed that a significant proportion of cryptocurrencies (39%) disappeared from the market, while only a small fraction (10%) survived for more than 1000 days. Our analysis revealed a significant negative correlation between cryptocurrency price and maximum and total supply, as well as a weak positive correlation between price and 24-hour trading volume. Moreover, we clustered cryptocurrencies into five distinct groups using their on-chain parameters, which provides investors with a more comprehensive understanding of a cryptocurrency when compared to those clustered with it. Finally, by implementing multiple classifiers to predict whether a cryptocurrency is risky or not, we obtained the best f1-score of 76% using K-Nearest Neighbor.

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.