ShumiShumi
Back to studies
Source noteMar 10, 20262 min read

Walk-Forward Performance, 2024-2025

Two years of out-of-sample trades with actual Binance funding costs applied per position. 26 wins out of 29 trades. Weak spots left in.

System design

  • Higher-timeframe regime filter to avoid trading against the macro trend.
  • Adaptive band system for entry timing.
  • Multi-day confluence window so isolated signals do not trigger trades alone.

Walk-forward protocol

  • Train window: 2021-01-01 to 2023-12-31.
  • Test window: 2024-01-01 to 2025-12-31.
  • Real Binance historical funding rates applied per trade.
  • Ten-asset universe with no exclusions.

Primary results

  • 26 wins out of 29 out-of-sample trades.
  • 120% cumulative return in the test window.
  • Average funding drag of roughly 1% per trade.
  • Five validation tests pass and three fail, all published.

Known limitations

  • The out-of-sample trade count is still small.
  • A few large winners drive most of the P&L.
  • Performance is regime-dependent: tested across bull and range-bound conditions in 2024-2025, not prolonged bear markets.