Food delivery
Multi-level demand forecasting for a food delivery client
Understanding needs
Our client needed to significantly upgrade their demand forecasting to keep pace with rapid growth.
Existing tools lacked the granularity to accurately predict demand at the store and hourly level, making it difficult to plan staffing, inventory, and CRM activity.
Connecting data
We built a multi-level time series forecasting system, integrating internal data (sales, CRM, marketing) with external variables (weather, events).
Models were built at market, store, and hourly levels using an ensemble of time series and regression-based methods.
Driving change
The models achieved 96–97% accuracy on daily test data. We also delivered interactive simulation tools for forecasting and scenario planning, plus a detailed analysis of sales drivers.
This empowered our client to significantly improve planning, reduce waste, and optimise operations during peak periods
If you have any data analytics questions or challenges please get in touch with:
Unbelievable impact in a short space of time. Analytics across diverse data was an eye-opener, providing clear direction to take to the CEO
Craig Milligan
Global Head of Consumer Analytics & Insights | Decision Sciences, Diageo