Forward-Look Bias Test Report

Strategy: POD3 0DTE SPX Iron Condor paper monitor  |  generated 2026-05-27 03:03

✗ FAIL — potential bias detected

Test 1: Shift-Lookahead

Compute sum(positions × asset_returns) under four position-time alignments. A causal strategy can be "cheated" by using tomorrow's positions — so the lead-1 case must inflate Sharpe substantially. If lagging by 1 day collapses Sharpe MORE than leading boosts it, the strategy already has built-in lookahead.

AlignmentSharpeNotes
same-day  pos[t]·ret[t] 14.886 Strategy's actual mechanism
lag-1  pos[t-1]·ret[t] 12.315 Stale by 1 day. Drop = +2.571
lead-1  pos[t+1]·ret[t] 13.176 Cheat with tomorrow's pos. Gain = -1.710
lead-5  pos[t+5]·ret[t] 10.694 Cheat further

Pass criteria: both must hold —
  • lead_gain ≥ 0.30 (cheating must add Sharpe)
  • lead_gain ≥ 0.80 × lag_drop (asymmetry signature)
Result: FAILED — lead-1 gain -1.710 < 0.3 threshold; strategy may have built-in lookahead (no room to cheat further)

Test 2: Position Autocorrelation

Day-over-day per-asset position autocorrelation. High AC means positions are stable and the shift test is reliable; low AC suggests positions are jumpy and the shift test less informative.

MetricValue
Assets included (≥ 100 active obs) 0
Mean autocorrelation0.000
Median0.000
Min0.000
Max0.000

Pass criteria: mean AC ≥ 0.50
Result: WARN — mean AC 0.000 < 0.5; positions jumpy, shift test less informative

Test 3: Truncate-and-Compare (SKIPPED)

Skipped — to enable, pass truncated_pipeline_fn and truncate_date to run_bias_test(). This is the gold-standard test: it re-runs your strategy with data physically truncated to ≤ T and verifies that day-by-day outputs match the full-data run exactly (modulo the boundary day).

Methodology

Generated by bias_test_kit. See METHODOLOGY.md for the full theory + worked example. The asymmetry check (lead_gain ≥ 0.8 × lag_drop) is the key innovation that catches built-in lookahead even when the absolute lead-gain looks fine — without it, synthetic cheats can slip through.