← Hub

Decision Model Review — GW33

Retrospective audit of Layers 1–3 · Top-50 managers · 3-GW replacement window

Findings & Recommendations

Synthesis from Layers 1–3 below. Supported findings only — inconclusive signals deliberately omitted.

Layer 1 — Chip deployment

  • Herd TC timing was anti-information. GW26 drew 29 of 84 TCs but had 8.41 pts mean regret vs 4.04 pts off-modal (only 41.7% of TCs landed on the optimal GW).
  • Herd BB timing also anti-information. GW33 drew 34 BBs with 17.56 pts mean regret vs 5.59 pts off-modal — ~3× worse. Modal-GW BB on the obvious DGW underdelivered relative to quieter weeks.
  • Free Hit usage is broadly value-additive. 80.0% of FH plays delivered positive delta vs the pre-FH squad (mean +15.0 pts). No evidence of systematic mistiming.

Recommendation: Do not auto-follow top-50 modal GW for TC or BB — the herd signal was anti-information this season. Continue eager Free Hit deployment; don't hold for a "perfect" DGW.

Layer 2 — Triage calibration

  • compute_verdict discriminates strongly. HOLD (n=483) averaged 4.22 pts/GW vs SELL (n=21,014) at 0.81 pts — a 3.41-pt gap. The model works.
  • Suggested threshold shift is overfit — keep current values. Grid-sweep winner (HOLD≥0.7) lifts the gap by ~0.4 pts but shrinks the HOLD bucket from 483 to ~84 rows (0.3% of population). Marginal lift is inside sampling noise. Do not change verdict_weights.json.

Recommendation: Keep verdict_weights.json at HOLD≥0.6 / MONITOR≥0.45. Re-evaluate after a full season of coverage; current grid-sweep lift is overfit to a tiny tail.

Layer 3 — Replacement quality

  • Premium IN-players dominate. ≥£10m tier wins 79.1% (mean +13.1 pts/3GW) vs <£6m at 54.6% (+3.5 pts) — 24.5pp gap. Bias trade targets toward premium when funds permit.
  • MID > FWD as trade targets. MID (n=1,379) wins 66.3% (+6.9 pts) vs FWD at 56.2% (+5.5 pts) — 10pp gap on substantive samples.
  • 62.2% overall win rate on n=3,050 trades. Trades are net positive but ~38% are wash-or-loss; verdict-driven transfers are not free yield.

Recommendation: When triage flags multiple SELLs, prioritise replacements that are premium MIDs. Treat budget enabler trades as marginal — only when needed for chip funding or short-term punt, not as default value plays.

Caveats on these findings

  • Hindsight: regret figures assume perfect information. The "anti-modal" finding does not mean the herd was irrational — it means the obvious play didn't pay this season.
  • Audit subjects are top-50 managers, not our 3 teams. Layer 1/3 reflects league-leader behaviour; per-team rows for SlowBuild / Yamal1 / MbappeSalah are pending data capture (TODO.md).
  • n=1 season. Findings are calibration evidence, not laws. Re-run end-of-season and after 2026/27 H1 before any structural model change.

Layer 1 — Chip Deployment Audit

Top-50 managers · GW1–33 · Hindsight regret: best alternative GW within same chip half

ChipEventsModal GW Median RegretP90 RegretHit Optimal GW
Triple Captain84GW266.0 pts14 pts41.7%
Bench Boost92GW339.0 pts21 pts25.0%
Free Hit60GW13delta vs pre-FH squad: +15.0 pts avg  |  80.0% positive
Wildcard89GW32descriptive only — yield analysis out of scope

Approximations: regret uses squad-actual-per-GW (manager's real captain/bench each week). Hindsight regret assumes perfect information — see report footer for caveats.

Layer 2 — Triage Model Calibration

Reconstructed verdicts via compute_verdict · avg_fdr fixed at 3.0 (neutral) · chance_next/tsb_pct from current snapshot

Current Hold Threshold
0.6
Current Monitor Threshold
0.45
Threshold Signal
Suggested: HOLD≥0.7 / MONITOR≥0.35 (current: 0.6/0.45)

Per-bucket next-GW points (current thresholds)

VerdictCountMean pts next GWMedian pts next GW
HOLD4834.222
MONITOR3,0793.012
SELL21,0140.810.0

Grid sweep — top 10 threshold pairs by HOLD−SELL discrimination gap

Hold threshMonitor threshHOLD meanSELL meanGap ↑
0.700.354.40.553.85
0.700.404.40.683.72
0.600.354.220.553.67
0.700.454.40.813.59
0.600.404.220.683.54
0.650.354.080.553.53
0.700.504.40.943.46
0.600.454.220.813.41
0.650.404.080.683.4
0.700.554.41.033.37

Layer 3 — Transfer Quality Audit

Top-50 managers · 3-GW point window · Skips FH/WC weeks

Total Trades
3,050
Win Rate
62.2%
Mean Δ pts (3 GW)
5.9
Median Δ pts (3 GW)
6.0

By IN-player position

PositionTradesWin RateMean ΔMedian Δ
GKP125WIN 62.4%4.6 pts5 pts
DEF912WIN 60.1%5.0 pts5.0 pts
MID1,379WIN 66.3%6.9 pts7 pts
FWD634WIN 56.2%5.5 pts4.0 pts

By IN-player price tier

Price TierTradesWin RateMean ΔMedian Δ
premium (≥10m)139WIN 79.1%13.1 pts13 pts
mid (8-10m)509WIN 68.4%8.4 pts8 pts
budget-mid (6-8m)1,247WIN 64.7%6.4 pts7 pts
budget (<6m)1,155WIN 54.6%3.5 pts4 pts