Case studies

A 28-cover Baner QSR ran on owner intuition and a WhatsApp group for three years. Thirty days into the Forkcast pilot, dish-level forecast accuracy hit 91% and over-prep dropped 68%.

The forecast is only as good as the feedback loop. A Khar casual-dining outlet started a 4-minute nightly close-out — actual covers vs forecast, top-5 dish deltas, one-line reason code. Three weeks later, next-week prep error dropped 34%.

A Kothrud veg-thali restaurant ran the same Shravan Monday surprise for six years — over-prepped sabudana, under-stocked thali components, ₹5k waste by 2pm. Thirty days into the Forkcast pilot, fasting-day prep matched actual covers within 8%.

Five dishes drove 44% of Swiggy revenue but lost money on every order after commission and packaging. A Hyderabad outlet fixed all five in 45 days — ₹1.8L/month recovered without dropping below 4.3 rating.

Hindkesari on FC Road ran spreadsheets for nine years. Twelve minutes of Petpooja onboarding later, the kitchen had a 30-day forward forecast — fasting days, weather, salary cycle included.

A 1,400 sqft Kothrud casual dining grew contribution margin 15 points in 90 days without raising prices on bestsellers or losing covers. Here is the before after, the 8 menu changes that mattered, and what the data shows.