Discover Regional and Size Effects in Global BitcoinBlockchain via Sparse-Group Network AutoRegressive Modeling

Year 2018
Author Ying Chen, Simon Trimborn, Jiejie Zhang
Link View Research Paper

Bitcoin / Cryptocurrencies / Society

Bitcoin blockchain has grown into an active global virtual money network with millions of accounts. We propose a Sparse-Group Network AutoRegressive (SGNAR) model to understand the dynamics of the cross-border transactions. It describes the money flows of virtual funds with focus on the regional and size effects, and provides insights into the inherent risk in the Bitcoin network at a global level. In particular, we develop a regularized estimator with two-layer sparsity, which enables discovering 1) the active regions with influential impact on the global network and 2) the size groups who lead the dynamic evolution of the Bitcointransaction network. Our study considers up-to-date Bitcoin blockchain, from February 2012 to July 2017, with all the transactions being classified into 60 groups according to their regions and transaction sizes. We found that the largest investors from North America and the medium-sized users from Europe were driving the network, while the other groups were either followers or isolated. The global connectivity was decreasing in the period of 2012 to 2015, but was enhanced in the recent years of 2016 and 2017. The inherent risk, measured as the risk of the Bitcoin network to fail, shrank lately compared to all the years up to 2015.