Evidence first.

How rows are scored

• The baseline gives every valid combination the same probability.
• Each lottery can use a versioned profile for its rule era, history length, bonus structure and prize-path coverage.
• Long, medium and short frequency, gaps and same-month history are estimated with strong statistical shrinkage.
• Noisy effects are pulled back towards zero and uncertain estimates receive an additional penalty.
• Number-pair effects are used only when they repeat across separate parts of the historical record.
• Rows with lower estimated sharing risk are preferred separately from draw probability.
• The portfolio optimiser rewards unused numbers, new pairs and the higher-order subsets that matter to that lottery's prize divisions.
• For two-barrel games, main numbers and the separately drawn bonus ball are distributed together so the complete board avoids duplicated joint coverage.
• The first row leads the ranking. Later rows can trade a small amount of base score for less duplicated coverage across the complete selection.

The evidence gate

The signal model learns from earlier draws, then predicts a later untouched period. It must improve the proper Brier probability score with a positive 95 percent confidence bound before any historical draw signal is switched on.

Lottery-specific model tournaments choose their settings inside earlier data, then face a separate outer holdout. This prevents the final test results from being used to select the formula.

Back-testing samples unseen draws across the available rule era. It compares match rates, probability scores and log loss with the fair-draw baseline.

Sharing and coverage

Player habits such as birthdays, lucky numbers and obvious patterns do not affect which balls are drawn. They can affect how many people share a pooled prize. This is why sharing value remains separate from probability evidence.

Coverage cannot make one valid row more likely to win. Across several rows, it reduces duplicated coverage and increases the number of distinct high-match outcomes represented by the published portfolio.

Rows stay fixed until verified history, lottery rules or the scoring method changes. Weather remains excluded unless exact pre-draw data demonstrates reliable value on unseen draws.

Public results accounting

Each published row is evaluated once against its assigned official draw. Repeated Generate clicks showing the same rows for the same draw do not multiply winning rows or prize value.

The draw-by-draw record shows the official numbers, the best matching Down To Luck row, any matched prize division and its theoretical prize value. These results do not mean a ticket was purchased, owned or claimed. Currencies remain separate and are never converted or added together.