WF03 · example_wf_03_anchored_purge_embargo.py WF03 Anchored Walk-Forward With Pre-OOS Purging
Inspect a weekly RSI mean-reversion strategy with an ANCHORED walk-forward, using a fixed purge plus a percentage extension before each OOS window.
Review the source on GitHub or return to all strategies.
What this example shows
This example shows how to build a workflow-level walk-forward validation research example with fold construction, parameter selection, diagnostics, logging and evidence capture.
The goal is educational: to demonstrate the full workflow for validation setup, search space definition, fold diagnostics, objective tracking and reproducible run logging.
Walk-forward diagnostic. 48-fold slice diagnostic from one full-period run. It demonstrates window construction, pre-OOS purging and diagnostic reporting, but it is not an independent per-fold refit or out-of-sample result.
Run setup
The ordinary configuration used by the published run—kept visible here and in the Python source.
UniverseXLB · XLE · XLF · XLI · XLK · XLP · XLU · XLV · XLY
Configured period2000-01-03 → 2026-01-01
BenchmarkSPY · SPDR S&P 500 ETF Trust
Initial capital$100,000
Data sourceyfinance
Engine / snapshot0.10.0 · a35f582c47dcd036
Walk-forward / OptimizationMode
1dGranularity
9Instruments
0Published plots
passedRun status
Dashboard
Compact evidence view built from the same run packet: metrics, plots and run metadata.
48 Folds
Slice diagnostic Mode
12/48 Negative slices
Metrics
This workflow emits diagnostics rather than a standard performance table.
Walk-forward diagnostic. 48-fold slice diagnostic from one full-period run. It demonstrates window construction, pre-OOS purging and diagnostic reporting, but it is not an independent per-fold refit or out-of-sample result.
Artifacts
Stable links that can be referenced from GitHub README files or external docs.
Run log
Tail of the execution log for this packet.
26 │ 2000-01 → 2015-01 │ 0.29 │ 2015-01 → 2015-07 │ 0.63
27 │ 2000-01 → 2015-07 │ 0.29 │ 2015-07 → 2015-12 │ 0.10
28 │ 2000-01 → 2015-12 │ 0.25 │ 2016-01 → 2016-07 │ 0.84
29 │ 2000-01 → 2016-07 │ 0.28 │ 2016-07 → 2016-12 │ 1.92
30 │ 2000-01 → 2016-12 │ 0.31 │ 2017-01 → 2017-06 │ -0.74
31 │ 2000-01 → 2017-06 │ 0.32 │ 2017-07 → 2018-01 │ 3.74
32 │ 2000-01 → 2018-01 │ 0.32 │ 2018-01 → 2018-07 │ 0.86
33 │ 2000-01 → 2018-07 │ 0.33 │ 2018-07 → 2019-01 │ -0.71
34 │ 2000-01 → 2019-01 │ 0.35 │ 2019-01 → 2019-07 │ 2.52
35 │ 2000-01 → 2019-07 │ 0.33 │ 2019-07 → 2020-01 │ 1.66
36 │ 2000-01 → 2020-01 │ 0.35 │ 2020-01 → 2020-07 │ -0.00
37 │ 2000-01 → 2020-07 │ 0.37 │ 2020-07 → 2020-12 │ 1.97
38 │ 2000-01 → 2020-12 │ 0.33 │ 2021-01 → 2021-07 │ 3.93
39 │ 2000-01 → 2021-07 │ 0.35 │ 2021-07 → 2021-12 │ 2.50
40 │ 2000-01 → 2021-12 │ 0.37 │ 2022-01 → 2022-07 │ -0.04
41 │ 2000-01 → 2022-07 │ 0.41 │ 2022-07 → 2022-12 │ 1.02
42 │ 2000-01 → 2022-12 │ 0.39 │ 2023-01 → 2023-06 │ 2.31
43 │ 2000-01 → 2023-06 │ 0.41 │ 2023-07 → 2024-01 │ 1.60
44 │ 2000-01 → 2024-01 │ 0.43 │ 2024-01 → 2024-07 │ 2.80
45 │ 2000-01 → 2024-07 │ 0.45 │ 2024-07 → 2025-01 │ 0.14
46 │ 2000-01 → 2025-01 │ 0.46 │ 2025-01 → 2025-07 │ 0.76
47 │ 2000-01 → 2025-07 │ 0.46 │ 2025-07 → 2025-12 │ 1.49
────────────────────────────────────────────────────────────────────────────────
AGGREGATE (IN-SAMPLE SLICES — not OOS)
Composite Sharpe (IS slice): 0.46 [5%: 0.16, 95%: 0.80]
CAGR (IS slice): 5.9% Overfit Ratio: 0.26
Max DD (IS slice): -49.2% Efficiency: 1.92
Sharpe Decay: +0.023/fold
Deflated Sharpe: n/a (in-sample; DSR not meaningful without independent trials)
PBO: n/a
(PBO unavailable: requires per-trial OOS evaluation; set WalkForwardConfig.pbo_trials=K (>=2) with an optimizer to evaluate top-K trials OOS per fold)
WARNINGS
⚠ PBO unavailable: requires per-trial OOS evaluation; set WalkForwardConfig.pbo_trials=K (>=2) with an optimizer to evaluate top-K trials OOS per fold
⚠ Walk-forward mode=slice_diagnostics: metrics are computed from a full-period NAV; pass backtester_factory for per-fold refit.
⚠ Fold 0: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 0: OOS Sharpe -0.94 is negative
⚠ Fold 0: overfit ratio inf > 2.5
⚠ Fold 1: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 1: OOS Sharpe -0.27 is negative
⚠ Fold 1: overfit ratio inf > 2.5
⚠ Fold 2: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 3: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 4: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 5: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 6: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 6: OOS Sharpe -0.10 is negative
⚠ Fold 6: overfit ratio inf > 2.5
⚠ Fold 7: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 8: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 8: overfit ratio 4.9 > 2.5
⚠ Fold 9: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 10: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 11: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 11: OOS Sharpe -0.03 is negative
⚠ Fold 11: overfit ratio inf > 2.5
⚠ Fold 12: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 12: OOS Sharpe -0.54 is negative
⚠ Fold 12: overfit ratio inf > 2.5
⚠ Fold 13: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 13: OOS Sharpe -0.87 is negative
⚠ Fold 13: overfit ratio inf > 2.5
⚠ Fold 14: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 14: OOS Sharpe -0.67 is negative
⚠ Fold 14: overfit ratio inf > 2.5
⚠ Fold 15: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 16: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 16: OOS Sharpe -0.18 is negative
⚠ Fold 16: overfit ratio inf > 2.5
⚠ Fold 17: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 18: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 19: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 20: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 21: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 22: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 23: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 24: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 25: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 26: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 27: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 27: overfit ratio 2.9 > 2.5
⚠ Fold 28: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 29: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 30: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 30: OOS Sharpe -0.74 is negative
⚠ Fold 30: overfit ratio inf > 2.5
⚠ Fold 31: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 32: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 33: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 33: OOS Sharpe -0.71 is negative
⚠ Fold 33: overfit ratio inf > 2.5
⚠ Fold 34: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 35: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 36: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 36: OOS Sharpe -0.00 is negative
⚠ Fold 36: overfit ratio inf > 2.5
⚠ Fold 37: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 38: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 39: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 40: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 40: OOS Sharpe -0.04 is negative
⚠ Fold 40: overfit ratio inf > 2.5
⚠ Fold 41: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 42: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 43: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 44: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 45: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 45: overfit ratio 3.2 > 2.5
⚠ Fold 46: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ Fold 47: slice diagnostics mode — metrics are sliced from the full-period NAV (no per-fold refit)
⚠ 12/48 folds have OOS Sharpe below 0.0
NOTE: slice_diagnostics mode — the metrics above are IN-SAMPLE
slices of ONE full-period run, not out-of-sample evidence.
Set QJ_WF_MODE=per_fold_refit for honest OOS validation.
Walk-forward traffic lights (IN-SAMPLE — indicative only):
MetricVerdict(name='overfit_ratio', value=0.2649033884528026, signal='green', description='< 1.5 — robust')
MetricVerdict(name='efficiency', value=1.921108632787444, signal='green', description='> 0.7 — robust transfer')
MetricVerdict(name='sharpe_decay', value=0.023476042871027544, signal='green', description='> -0.01/fold — stable')