Modeling Bitcoin Blocks and Price Jumps with Hawkes Processes

Summary

The paper models Bitcoin block arrivals and price jumps using a multivariate Hawkes process, a point-process framework that represents events as capable of exciting later events. It uses publicly available blockchain data and estimates model parameters by maximum likelihood. This setup is intended to capture both self-excitation within event streams and cross-excitation between block mining and Bitcoin price volatility.

The reported results indicate that Bitcoin price volatility increases the block mining rate, while Bitcoin investment returns exhibit mean reversion. Quantile-quantile plots show a better fit to the blockchain data for the Hawkes model than for a Poisson model. These findings describe statistical relationships and model fit; the short account does not provide parameter estimates, dataset scope, predictive performance, or evidence that the results support a profitable trading strategy.

Key ideas

• A multivariate Hawkes process is used to represent Bitcoin block arrivals and price jumps.
• The model parameters are estimated by maximum likelihood from public blockchain data.
• The framework captures self-excitation and cross-excitation among event streams.
• The reported analysis finds that Bitcoin price volatility boosts the block mining rate.
• Bitcoin investment returns are reported to mean-revert, and quantile-quantile plots favor Hawkes over Poisson fit.

Tags

# Hawkes Process Modeling of Block Arrivals in Bitcoin Blockchain


# Hawkes Process Modeling of Block Arrivals in Bitcoin Blockchain









The paper constructs a multi-variate Hawkes process model of Bitcoin block arrivals and price jumps. Hawkes processes are selfexciting point processes that can capture the self- and cross-excitation effects of block mining and Bitcoin price volatility. We use publicly available blockchain datasets to estimate the model parameters via maximum likelihood estimation. The results show that Bitcoin price volatility boost block mining rate and Bitcoin investment return demonstrates mean reversion. Quantile-Quantile plots show that the proposed Hawkes process model is a better fit to the blockchain datasets than a Poisson process model.

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.