Skip to content
Nocta
See all work
AI Forecasting · Retail Analytics/2026

FuelCast

SPECIMENSPECIMENSPECIMENSPECIMEN

A demand-forecasting and business-intelligence platform for fuel retail — predicting fuel and shop demand, catching margin leaks, and answering plain-English questions from operators.

ClientShell South Africa — multiple forecourts

Client anonymized. Every figure and chart on this page uses synthetic data calibrated to look realistic — we never publish a client's live numbers.

0
demand horizon, per grade
0
more accurate than the naive baseline
0
shop categories forecast for ordering
0
live data refresh cycle

Fuel forecourts run on thin margins and perishable stock. FuelCast forecasts fuel and shop demand up to 90 days out, turns it into ordering decisions, and puts a plain-English AI assistant in front of the whole thing so a manager can just ask.

FuelCast / interactive demo[ SYNTHETIC DATA ]
[ FUELCAST ]Forecourt overview

Demand forecasting & shop ordering

Live · 10 min

Forecast demand

281k L

4.2%next 30d

Gross margin

22.4%

1.3ppvs 21.1% LM

Deadstock flagged

R 38.2k

12%at risk · MoM

Data quality

99.2%

0.4ppPOS reconciled

[ DEMAND FORECAST ]

Petrol 95 · liters / day

Actual → forecastSeasonal-naive80% band
7.2k8.7k10.1k11.6k−59dToday+30d

[ STOCK ORDERING ]

Recommended · next 7 days

  • Beverages
    1240 u
  • Snacks
    880 u
  • Bakeryspoilage risk
    560 u
  • Energy
    420 u
  • Delispoilage risk
    340 u

[ ASK FUELCAST ]

Answers from the forecast · figures synthetic

Ask about demand, ordering, or margins — I answer from the live forecast. Every figure here is synthetic.

Interactive / built with synthetic data for this page

[ THE CHALLENGE ]

90-daydemand horizon, per grade

A fuel retailer's real signal is buried: pump sales, shop tills, and card terminals reconcile only at month-end, stock spoils before anyone notices, and pricing is regulated to the cent. The operator needed to see demand coming, order the right stock, and understand why — without hiring a data team.

How we built it

From signal to shipped.

01

Foundation-model forecasting

A TimesFM 2.5 time-series model forecasts fuel demand per grade and shop demand per category, with South-Africa-specific covariates — paydays, fuel-price change days, holidays, weather. Always benchmarked against an honest seasonal-naive baseline; the model roughly halved the error.

02

Decisions, not just charts

Forecasts feed a stock-ordering engine — newsvendor logic for perishables, safety-stock for packaged goods — so the output is 'order this much', not a graph a manager has to interpret.

03

An operator's BI dashboard

A themed dashboard surfaces demand, profit & loss, deadstock, and data-quality — with reconciliation gates that flag bad point-of-sale entries instead of trusting them blindly.

04

Ask, in plain English

An in-dashboard AI assistant routes questions to read-only tools (SQL, the forecaster, the calc engine), never invents numbers, and stamps every figure. Non-technical staff get answers without learning the tool.

What shipped.

PythonTimesFM 2.5DuckDBPlotly / DashOpenRouterDocker

Fuel demand forecast per grade with quantile bands, ~2× tighter than the naive baseline.

Six shop categories forecast and converted into concrete stock-order quantities.

Live ingestion on a 10-minute cycle, deployed and running unattended.

A plain-English assistant that lets any operator query the business directly.

[ NEXT PROJECT ]

Outreach Engine