SQUEEZE RADAR — predicted vs real, live

Every price burst on BTC/ETH/SOL gets a live probability of completing a ±0.16% move, scored at +20/60/120/180/240/300s by a fixed logistic model. Every prediction and its outcome is logged automatically — this table recomputes from that log. No selection, no edits. Columns = predicted-probability buckets; each cell shows average predicted → realized frequency.

checkpoint0-20%20-40%40-60%60-80%80-100%
+20s34% → 56% n=7050% → 66% n=21269% → 73% n=24892% → 89% n=314
+60s32% → 52% n=11950% → 61% n=19769% → 76% n=20091% → 90% n=234
+120s17% → 38% n=2431% → 43% n=12750% → 65% n=18870% → 77% n=16489% → 88% n=130
+180s15% → 23% n=3930% → 52% n=15749% → 57% n=15070% → 76% n=11988% → 88% n=76
+240s15% → 27% n=4131% → 44% n=8450% → 52% n=7168% → 73% n=3087% → 74% n=19
+300s13% → 24% n=5829% → 38% n=8248% → 60% n=5068% → 63% n=1991% → 67% n=6

Bursts resolved so far: 850 · completed: 644 (76%) · updated 2026-06-12 16:23 UTC (10-min cache)

Confirmed icebergs (level absorbed ≥1× its displayed size, multi-tranche tracking): 1326 resolved — held 0 · broken 391 · pulled 42 · consumed 893 · median executed/displayed 2.0× (survival stats only — no directional claim. Frey & Sandås (QJF 2017): a heavily-executed iceberg = demand already met → LESS follow-through; our 527k-episode base-rate study agrees: P(hold) does not rise with the multiple)

Honest notes: scoring is live since 2026-06-10 — early samples lean on a high-volatility regime; the mix broadens as days accumulate. The model predicts WHEN/WHETHER a move completes, never direction (we measured direction predictability at these horizons: it is not there). Not financial advice. ← Squeeze Radar