Observed arrival · 2026-09-29
VIVES Forecasting Lab’s Playable Forecasts
A university forecasting group presents interactive demos for meal demand, inventory replenishment, and predictive cybersecurity.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Foodservice planners and retail inventory teams
- Worth noticing
- The meal demo offers controls for weather, exams, holidays, campus events, and promotions, alongside an 80% prediction interval.
Field notes
The meal-planning exercise exposes weekday, weather, menu, exam-period, school-holiday, campus-event, and price-promotion inputs, then frames the decision as how many meals to cook. Its stated model uses sales history and gradient-boosted trees such as LightGBM, producing per-day and per-dish forecasts with prediction intervals; the inventory section separately explains demand over supplier lead time and uncertainty-scaled safety stock.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
One card from the complete issue