Search:
Match:
1 results

Analysis

This paper addresses the fragility of backtests in cryptocurrency perpetual futures trading, highlighting the impact of microstructure frictions (delay, funding, fees, slippage) on reported performance. It introduces AutoQuant, a framework designed for auditable strategy configuration selection, emphasizing realistic execution costs and rigorous validation through double-screening and rolling windows. The focus is on providing a robust validation and governance infrastructure rather than claiming persistent alpha.
Reference

AutoQuant encodes strict T+1 execution semantics and no-look-ahead funding alignment, runs Bayesian optimization under realistic costs, and applies a two-stage double-screening protocol.