Methodology
How Bowling Data measures demand
One written rulebook for every venue; a changed rule is a new model version.
Observation
- Every bookable slot is observed as inferred booking signals in public data while it is on sale.
- Only public data, with no logins and no private accounts. Every observation is kept as received and never edited.
From signals to bookings
- A slot is one bookable start time with a capacity counter, in the venue’s own unit (a lane per start time, or a lane for a booked duration).
- Changes in what a slot offers the public are read as inferred booking signals; bookings are inferred from those signals, never assumed.
- Signals that cannot be told apart stay unknown; when a slot’s final state is not observed, its bookings are a modeled range, not a guess.
Figures
- Utilization: the share of offered capacity booked by each slot’s start, with coverage (the share observed through to the end).
- Revenue (GBV): inferred bookings × the venue’s published prices, packages and memberships, as an estimate. Prices are never backdated.
- Every estimate carries an 80 % interval (P10–P90) and an A–D grade for its width.
- Markets: venue figures combine into market totals, each with its own range.
- Next-day forecast: published only when enough comparable history supports it.
Rules
- Unknown is never zero: missing or conflicting observations widen intervals and lower coverage.
- Raw is truth: every observation is kept as received and never edited; every figure is rebuilt from them.
- Models are versioned and proven against each venue’s raw data; released versions are frozen.