Classifying Price Patterns to Compare Cryptocurrency and Stock Markets

Summary

This study asks whether cryptocurrency investors trade differently from stock investors and uses asset price histories as evidence of those behaviors. It first applies multiple machine-learning models to classify cryptocurrency and stock time series observed over the same period. The reported high classification accuracy suggests the two groups have distinguishable price patterns, though classification alone does not establish why those differences arise or whether they persist.

The authors then calculate time-series characteristics—including distributional moments, extremes, and autocorrelation at several orders—and use logistic regression, random forests, support vector machines, and other classifiers to assess their explanatory value. The results indicate that these features help separate the two asset groups. The document does not provide details on sampling choices, out-of-sample validation, or specific accuracy figures, so the strength and trading relevance of the reported distinctions cannot be independently assessed from this summary. The method is comparative analysis, not a trading rule or evidence of profitable returns.

Key ideas

• Price time series can be used to distinguish cryptocurrency behavior from stock behavior.
• The study reports high accuracy when classifying the two asset groups over the same period.
• Distributional statistics and autocorrelation features help explain the observed pattern differences.
• Logistic regression, random forests, and support vector machines are among the tested models.
• Classification evidence identifies differences but does not establish their causes or profitability.

Tags

# Classification-Based Analysis of Price Pattern Differences Between Cryptocurrencies and Stocks


# Classification-Based Analysis of Price Pattern Differences Between Cryptocurrencies and Stocks









Cryptocurrencies are digital tokens built on blockchain technology, with thousands actively traded on centralized exchanges (CEXs). Unlike stocks, which are backed by real businesses, cryptocurrencies are recognized as a distinct class of assets by researchers. How do investors treat this new category of asset in trading? Are they similar to stocks as an investment tool for investors? We answer these questions by investigating cryptocurrencies' and stocks' price time series which can reflect investors' attitudes towards the targeted assets. Concretely, we use different machine learning models to classify cryptocurrencies' and stocks' price time series in the same period and get an extremely high accuracy rate, which reflects that cryptocurrency investors behave differently in trading from stock investors. We then extract features from these price time series to explain the price pattern difference, including mean, variance, maximum, minimum, kurtosis, skewness, and first to third-order autocorrelation, etc., and then use machine learning methods including logistic regression (LR), random forest (RF), support vector machine (SVM), etc. for classification. The classification results show that these extracted features can help to explain the price time series pattern difference between cryptocurrencies and stocks.

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.