₹
What will we sell?
Revenue and order forecasts by outlet, with period comparisons and a range, not one unexplained number.
Explore →Restaurant Forecasting · Live
Restaurant forecasting that turns tomorrow’s demand into today’s prep plan.
Openfluid turns restaurant history into a daily operating view: expected revenue, orders, menu-item demand, ingredient requirements and likely excess, by outlet, with the assumptions visible.
3-outlet sample dataset730 daily observationsNo invented cost or waste claims
Saturday forecast1 August 2026
Sample dataRevenue₹1.69LAcross 3 outlets
Orders281Seasonal baseline
Top item115Chicken Dum Biryani portions
Jubilee Hills₹61,126 · 95 orders
Gachibowli₹59,089 · 101 orders
Madhapur₹48,407 · 85 orders
Illustrative forecast generated from the attached 730-day synthetic restaurant dataset. It is not a customer result.
Openfluid is restaurant forecasting software that uses sales and operating history to forecast revenue, orders, menu-item demand and ingredient requirements by outlet. It helps restaurant teams decide what to prepare, purchase and review before service.
The product
Five questions operators ask before service
Openfluid is not positioned as a generic analytics dashboard. Each module is tied to a decision that has to be made before purchasing, preparation or service.
◫
What should the kitchen prepare?
Item-level demand converted into preparation quantities that can respect buffers, batches and holding limits.
Explore →▦
What ingredients will we need?
Recipe-linked requirements compared with closing stock so buyers see the actual gap.
Explore →↘
Where are we over-preparing?
Forecast excess is separated from recorded waste, so prevention is not confused with measurement.
Explore →✦
What changed, and why?
Forecast Chat returns structured answers from available data and states when a requested input is missing.
Explore →□
What comes after restaurants?
Retail Forecasting will apply the same discipline to store-SKU demand, replenishment and transfers.
Explore →Sample week
A real example is more useful than a broad promise
The prototype uses a fictional Indian restaurant dataset created for model simulation. The examples below are traceable to that file and should not be presented as customer outcomes.
Last recorded week₹10,53,6031,768 completed orders · ₹596 average order value
The preceding week in the same synthetic dataset recorded ₹10,35,489. That is a 1.7% increase, not a claim of product lift, simply the historical comparison an operator needs before reviewing the next forecast.
The next step is operational: identify which outlet, item or calendar effect created the change, then decide whether preparation and purchasing should move with it.
40 / 38 / 37Forecast Chicken Dum Biryani portions for Jubilee Hills, Gachibowli and Madhapur on the next Saturday.
517 vs 12Seven-day packaging-box requirement versus recorded closing stock at Jubilee Hills: a purchasing exception, not just a chart.
42.8 portionsRecorded Chicken Dum Biryani waste in the latest seven days. Actual waste remains distinct from forecast excess.
Why it exists
Dashboards explain the past. Openfluid prepares the next decision.
Historical reporting still matters. The difference is that Openfluid uses the history as an input to a future operating decision, then records what the team approved.
Typical reporting question
What happened last week?
- Revenue by outlet
- Item sales and channel mix
- Closing stock and recorded waste
→
Openfluid operating question
What should change before tomorrow?
- Which outlet needs a different plan?
- Which items need more or less preparation?
- Which ingredients will run short?
- Which excess should be reviewed before production?
Trust before claims
The product is explicit about the boundary of the data
A forecasting product loses credibility when it fills missing fields with plausible-looking numbers. Openfluid should show the gap instead.
Sales and order history
Revenue, completed orders, outlet, item and calendar fields support demand forecasting and period comparisons.
Inventory and waste
Ingredient usage, closing stock, preparation and waste records are separate operational inputs. POS sales alone cannot reveal actual kitchen waste.
Profitability and vendor economics
Channel commissions, recipe costs, vendor prices, labour and cash flow must be connected before Openfluid can answer those questions responsibly.
Start with one decision, not a transformation programme.
Share the source file and the planning question. The first review should identify what can be forecast now, what needs more data and how success will be measured.