Research area 08
Forecasting and decision intelligence
Models that forecast change over years, not seconds, and the decision frameworks that turn a probabilistic forecast into an action with a known risk.
- forecasting
- decision-theory
- uncertainty
- long-horizon
Many of the most valuable predictions have long horizons: where development will intensify, which markets will transition, what a region’s infrastructure will need. Long horizons make evaluation hard, leakage easy, and overconfidence tempting. Decision intelligence is the practice of connecting such forecasts to the actual decision, with its costs, options, and timing, and of reporting what the model does not know.
What we work on
- Out-of-time validation. Backtests that respect what was knowable, with placebo events and continuation baselines.
- From forecast to decision. Framing outputs as probabilities with calibrated intervals and explicit decision thresholds.
- Separating questions. Keeping “where is change emerging” and “what is it worth” as separate models until each is validated.
Projects in this area
Land Alpha
An early-stage research programme testing whether fragmented public and local data can identify land-market transitions before those changes are fully reflected in market signals.
- Spatial and geospatial intelligence
- Forecasting and decision intelligence
- Data science and applied machine learning
LandInvest on Google Cloud
The data platform and Market Explorer application behind LAISER's land-investment research, built as a data lake, BigQuery layer, serving export, and Cloud Run web app with pipeline-only deploys.
- Big data, analytics, and ML systems engineering
- Spatial and geospatial intelligence
- Forecasting and decision intelligence