🤖 AI Summary
This study investigates stable cross-asset microstructural patterns in cryptocurrency limit order books and their predictive power for short-term returns. Leveraging second-level data from Binance Futures, the authors employ a unified CatBoost framework with a direction-aware GMADL objective function and time-series cross-validation to systematically analyze the stability of feature importance and SHAP dependence across multiple assets. Findings are interpreted through the lens of classical market microstructure theory. Notably, the paper empirically validates adverse selection theory by contrasting market-making and taker strategies during flash crash events, thereby uncovering systemic risks inherent in algorithmic trading. The research reveals highly consistent and transferable feature patterns across assets of varying market capitalizations—such as BTC and LTC—and demonstrates their practical trading viability through conservative order book backtesting.
📝 Abstract
We document stable cross-asset patterns in cryptocurrency limit-order-book microstructure: the same engineered order book and trade features exhibit remarkably similar predictive importance and SHAP dependence shapes across assets spanning an order of magnitude in market capitalization (BTC, LTC, ETC, ENJ, ROSE). The data covers Binance Futures perpetual contract order books and trades on 1-second frequency starting from January 1st, 2022 up to October 12th, 2025. Using a unified CatBoost modeling pipeline with a direction-aware GMADL objective and time-series cross validation, we show that feature rankings and partial effects are stable across assets despite heterogeneous liquidity and volatility. We connect these SHAP structures to microstructure theory (order flow imbalance, spread, and adverse selection) and validate tradability via a conservative top-of-book taker backtest as well as fixed depth maker backtest. Our primary novelty is a robustness analysis of a major flash crash, where the divergent performance of our taker and maker strategies empirically validates classic microstructure theories of adverse selection and highlights the systemic risks of algorithmic trading. Our results suggest a portable microstructure representation of short-horizon returns and motivate universal feature libraries for crypto markets.