Forecasting models
Time-series and regression models for demand, yield, consumption and other quantities that change over time.
Services
Machine learning and forecasting
We build machine learning systems that use historical and real-time data to estimate what happens next, catch unusual patterns and support better decisions.
When machine learning helps
- You need to estimate what happens next from historical or sensor data.
- Unusual patterns should be caught before they turn into problems.
- Manual inspection or classification does not scale.
- Decisions depend on trade-offs that can be optimised.
What we build
Anomaly and pattern detection
Baselines per asset, building or site, and detection of deviations that deserve attention.
Classification and prediction
Models that label, score or rank, evaluated against outcomes you already know.
Computer vision
Extracting information from images, such as detecting and measuring objects.
Optimisation
Choosing between options under constraints, using the predictions as input.
How a project runs
Every project follows the same four steps.
- 01Understand
- 02Build
- 03Validate
- 04Deploy
Where we have applied it
Client work
Asset Circles
Sensor, weather and equipment data turned into building-specific anomaly detection and advice.
Read the case →Pilot
Vink Farming
Earlier signals on crop development and yield from imagery, parcel and weather data.
See Vink Farming ↗Pilot
FlyingVink
Estimating where drone cleaning is economically attractive for a building.
See FlyingVink ↗