Applications and problems

Forecasting with public data

A useful forecast must be comparable with what happened afterwards. These workflows therefore distinguish the data available at prediction time, the baseline, the horizon and the error once the outcome matures.

What matters

The problem comes before the model.

  • Point-in-time vintages and prevention of look-ahead bias.
  • Comparison with simple baselines before assigning value to more complex models.
  • Intervals, probabilities and prospective error tracking rather than retrospective charts alone.

Lab Intelligence approach

Sources, assumptions, checks, versions, metrics and limitations remain visible. A more complex technique is used only when it adds value over an understandable baseline.

How the method works →