One page for everything gold: spot & technicals, macro drivers, prediction-market odds, positioning flows — and yes, the astrology pillar, held to the same scoreboard as everything else. Every signal is weighted by its measured track record, not by belief.
Each pillar earns its weight from measured forecast skill (Brier score vs a random-walk baseline, 26-week rolling window). Defaults below are the engine's earned weights; drag to run your own scenario — the balance, composite and bull/bear split recompute live.
Snapshot from this issue — the living board rebuilds every 6 hours with item-level weights and decay.
Seven scenarios for $4,500 gold under a Fed hike, a $150 oil shock, and a Treasury exodus. In the worst one, gold falls 12% in sixty days — then rises 43% in twelve months.
Issue No. 17 · 2026-10-26 — Bottom line: gold closed the week at $4,003.77, -3.82% on the week, with the 10-year real yield -10bp at 2.64%.
The astrology pillar is scored like every other: each call is registered before the event and graded against the price afterwards. Its weight in the composite is whatever that record has earned — no more.
alerts.py) ships in the next update. This log will show real threshold crossings, regime flips, and pillar-direction changes as they fire to Telegram.Alert triggers: |price| crosses 50/200-DMA · weekly close beyond range boundaries · prediction-market move ≥15pts/week on Fed or geopolitics contracts · any pillar flips sign · composite crosses ±25 · central-bank monthly flow beyond ±30t.
| Pillar | Calls scored (26w) | Hit rate | Brier score ↓ | Skill vs random walk | Earned weight |
|---|---|---|---|---|---|
| Macro & Flows Real yields, DXY, Fed path, CB buying, ETF flows |
0 | — | — | +0% | 4% (probation) |
| Price Action MA regime, RSI, structure, volume |
16 | 58.3% | 0.246 | +0% | 72% |
| Prediction Markets Polymarket & Kalshi: Fed, CPI, geopolitics, gold brackets |
8 | 37.2% | 0.265 | +0% | 4% (probation) |
| Astrology Pre-registered transit rules only |
28 | 53.5% | 0.249 | +0% | 19% |
Every call is pre-registered. A signal is only scoreable if it was logged before its window opened, with a direction, a probability, a horizon and a threshold. No retrofitting, no "the transit explains the dip" after the fact — that discipline is what was missing from v1.
Probabilities, not prophecies. Pillars emit statements like "62% that gold closes above $4,200 within 5 sessions." These are scored with the Brier score, which rewards both being right and knowing how sure you were.
Weights are earned, not assigned. Each pillar's weight is proportional to its skill above a random-walk baseline over a rolling 26-week window, updated with exponential decay (recent skill counts more). A pillar that can't beat a coin flip decays toward a 5% probationary floor, then to zero after two failed quarters.
The astrology question answers itself. Whether astrology "works" for gold stops being a debate: it is a number in the table above, recomputed weekly. Currently it earns 19% — behind the flat-25% baseline every pillar starts at. The engine is agnostic; the scoreboard is not.
Baselines keep everyone honest. The composite is benchmarked weekly against (a) random walk, (b) simple 20-day momentum, (c) "always bullish." If the engine can't beat all three over a rolling year, the whole methodology gets revised — that rule is itself part of the methodology.
Regime awareness. The price-action pillar reads the live weekly/daily trend regime (bull, bear, or neutral) directly from moving-average structure — not a separate "hidden layer," just what the MAs say right now: weekly NEUTRAL, daily BEAR. Tracking pillar skill separately per regime (does an edge hold up differently in trends vs ranges?) is on the roadmap, not built yet.