Fragmentation, Price Formation and Cross-Impact in Bitcoin Markets

In the light of micro-scale inefficiencies due to the highly fragmented bitcoin trading landscape, we use a granular data set comprising orderbook and trades data from the most liquid bitcoin markets, to understand the price formation process at sub-1-second time scales. To this end, we construct a set of features that encapsulate relevant microstructural information over short lookback windows. These features are subsequently leveraged, first to generate a leader–lagger network that quantifies how markets impact one another, and then to train linear models capable of explaining between 10% and 37% of total variation in 500 ms future returns (depending on which market is the prediction target). The results are then compared with those of various PnL calculations that take trading realities, such as transaction costs, into account. The PnL calculations are based on natural taker strategies (meaning they employ market orders) associated with each model. Our findings emphasize the role of a market's fee regime in determining both its propensity to lead or lag, and the profitability of our taker strategy. We further derive a natural maker strategy (using only passive limit orders) which, due to the difficulties associated with backtesting maker strategies, we test in a real-world live trading experiment, in which we turned over 1.5 M USD in notional volume. Lending additional confidence to our models, and by extension to the features they are based on, the results indicate a significant improvement over a naive benchmark strategy, which we also deploy in a live trading environment with real capital, for the sake of comparison.