momentum devandClaude Fable 5
ab2810896c
iv_exit_config replays ANY target/breakeven/trail combo through the shared exit engine vs the live-exit baseline — reusable way to adjudicate exit numbers. Counterfactual over setup fires: v1 (slow, 1.37R median winners) gains most from prior_low trailing (win 17->24%, +0.036R); pm1 (fast, 2.64R median, 10R tail) gains most from NO target + step0.5 (+0.273R, win 24->34%) — the fixed target throws away pm1's fat tail. Registered both as tracked experiments. +test. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
10 lines
707 B
JSON
10 lines
707 B
JSON
{
|
|
"id": "exit_pm1_fattail",
|
|
"hypothesis": "Removing the fixed target and step-locking profit (trail_r_step=0.5) captures the premarket fat tail (pm1 winners median 2.64R, peak 22min, tail to 10R) that a target-2R cap throws away — the biggest exit delta measured (+0.27R over the live exit).",
|
|
"population": {"min_entry_gap_pct": 0.10, "min_day_volume": 300000, "price_min": 2.0, "price_max": 20.0},
|
|
"intervention": {"kind": "exit_config", "exit_cfg": {"target_r": 0.0, "breakeven_at_pct": 0.05, "trail_r_step": 0.5}},
|
|
"bars": {"expR_delta_min": 0.05, "min_n": 300},
|
|
"futility": {"min_n": 500, "expR_delta_max": -0.03},
|
|
"fidelity": {"atr_frac": 0.25, "spread_mult": 3, "adverse_ticks": 1}
|
|
}
|