Paper Type

ERF

Abstract

This study investigates the degree to which Bitcoin pricing adheres to the Efficient Market Hypothesis (EMH). By employing Decision Tree and Random Forest algorithms, we explore whether publicly available macroeconomic, financial market, and Bitcoin-specific variables can accurately predict Bitcoin price movements. Results show consistently low Mean Absolute Error (MAE) and Mean Squared Error (MSE) forecasts for both models, with Random Forest yielding comparatively smaller errors. These findings indicate that public information is integrated into Bitcoin’s price in ways consistent with weak-form EMH. However, we also highlight that incremental gains from more sophisticated algorithms diminish rapidly, which suggests a high level of market informational efficiency.

Paper Number

2190

Author Connect URL

https://authorconnect.aisnet.org/conferences/AMCIS2025/papers/2190

Comments

SIGDSA

Author Connect Link

Share

COinS
 
Aug 15th, 12:00 AM

Bitcoin Price Forecasting with Decision Trees and Random Forests: Evidence of Market Efficiency

This study investigates the degree to which Bitcoin pricing adheres to the Efficient Market Hypothesis (EMH). By employing Decision Tree and Random Forest algorithms, we explore whether publicly available macroeconomic, financial market, and Bitcoin-specific variables can accurately predict Bitcoin price movements. Results show consistently low Mean Absolute Error (MAE) and Mean Squared Error (MSE) forecasts for both models, with Random Forest yielding comparatively smaller errors. These findings indicate that public information is integrated into Bitcoin’s price in ways consistent with weak-form EMH. However, we also highlight that incremental gains from more sophisticated algorithms diminish rapidly, which suggests a high level of market informational efficiency.

When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.