Features‎ > ‎

Model development

Cancha automates:
  1. Geometallurgical model generation
  2. Statistical validation, 
  3. Model ranking 
While models are ranked and recommended, model validation and selection should be done by the user.  

Tyler Vigen has an excellent website that explains why automated model selection is dangerous.

If all data sets looked like this, then Cancha would not be needed:

In the real world, multi-linear regression is confused by domains that overprint:

Cancha can separate domains, and then perform regression on each:

With little preparatory work by the user, Cancha rapidly generates and ranks models from thousands of data features and sample characteristics, such as:
  • Head assays
  • Automated modal mineralogy
  • Lithology and alteration rock types
  • Geological logs
  • Spatial location