Experiment ID:
dsp_kalman_trend· Market:BTCUSDT(1d, 390 bars, 2025-09-25 → 2026-10-19) · Mathematical Mode:DSP
1. Hypothesis & Mathematical Architecture
Enters when state-space Kalman(0.05) crosses above Ehlers SuperSmoother(21) under Choppiness < 58.5 and ADX > 18 regime confirmation, riding trends with Chandelier & Breakeven stops.
- Studio Rule Specification: Build a DSP trend strategy on BTCUSDT 1d using Kalman(0.05) crossing above Ehlers SuperSmoother(21), gated by Choppiness(14) < 58.5 and ADX(14) > 18, with 2.2x ATR stop, 4.5x ATR target and 1.4x ATR breakeven ratchet.
- Friction Assumptions: 0.06% taker fee + 5 bps slippage per leg.
2. Measured Backtest & 70/30 Out-of-Sample (OOS) Audit
| Metric | Full Sample (390 bars) | In-Sample (70% IS) | Out-of-Sample (30% OOS) |
|---|---|---|---|
| Net Return | 0.00% | 0.00% | 0.00% |
| Sharpe Ratio | 0.00 | 0.00 | 0.00 |
| Sortino Ratio | 0.00 | 0.00 | 0.00 |
| Profit Factor | 0.00 | 0.00 | 0.00 |
| Win Rate | 0.0% | 0.0% | 0.0% |
| Max Drawdown | -0.00% | -0.00% | -0.00% |
| Total Trades | 0 | 0 | 0 |
3. Indicator Information Coefficient (Spearman IC) Audit (dsp_spread)
_Script outputs direct boolean triggers; trade-level OOS metrics serve as primary evidence._
4. Reproducible formula.js Script
// DSP Kalman & SuperSmoother Trend Signal
kf = kalman(close, 0.05)
ss = supersmoother(close, 21)
spread_z = zscore(kf - ss, 30)
plot dsp_spread = spread_z
plot regime_ok = chop(14) < 58.5 and adx(14) > 18
plot entry_long = crossover(kf, ss) and regime_okVerify & Fork in One Click
- Open in Strategy Studio — Modify rules, run 4-fold Walk-Forward or 2,000-path Monte Carlo simulations.
- Open in Indicator Lab — Adjust filter parameters and inspect IC decay and quintile monotonicity.
- Academy Cookbook — Browse all verified quantitative blueprints.
Reproducible backtest experiments, out-of-sample audits, and indicator IC studies on live market bars.