UK49s results are random lottery outcomes. Research models rank historical patterns and do not establish a reliable ability to predict future winning numbers. Experimental signals may disappear out of sample. 48 tests run. 0 validated edges found above baseline.
V8 Research · Experimental
Candidate Engine
Ranking scores for all 49 numbers, generated before the draw. Ranking is not a probability and does not identify future results.
How This Works
Method description — no outcome claims
Daily Predict (Signal Engine)
Analyses the most recent draws using pattern signals: REPEAT (numbers from last draw), MULTI (numbers appearing across multiple draw types), T1 Mirror (transition pairs), and Booster signals. Explains WHY each number scored high.
Candidate Engine (Ranking Engine)
Combines 10 signals (frequency, recency, gap, repeat, pairs, transitions, range, odd/even, rhythm, hot balls) using Borda count with draw-type-specific weights. BT and DT weight trending/recency more heavily based on backtest evidence. Produces the Top 6 ranked candidates.
Trending Pool Filter
Numbers currently appearing at elevated rates vs their historical average (trending count ≥ 12 from 49s.co.uk). Yesterday 18 of 24 drawn numbers came from this pool. Used as a cross-check: candidates inside the trending pool have stronger evidence.
Trending alignment — research indicator only. Pool membership does not indicate or guarantee that a number will be drawn.
Experimental model — unvalidated
In testing. No result here is confirmed out-of-sample. Candidate output is experimental; only the Prospective Audit page scores it after the draw.
Selection
Draw type and ranking engine
🍳 Brunchtime — top-ranked candidates
GET /api/candidates/brunchtime