Metrics

I see that metrics are a bit basic. I dealt with production ML models, DS, BA, and policy makers might want to use more advanced metrics.

For example, if it is a classification problem then:

Discrimination Power:
- Area Under Curve (AUC ROC).
- Kolmogorov-Smirnov Statistic (KS)
- Accuracy Ratio (AR) based on Accuracy Profile
- Pietra index
- Precision at Recal

Distribution and Skew:
- Brier score
- Hosmer-Lemeshow (HL)
- Jensen-Shannon distance (JSD)
- Herfindahl-Hirschman Index (HHI)

Arguable, for ranking you would use other metrics. Best place would be to make a server of literature and recommendations from consulting companies like BCG or Accenture on what they recommend for the enterprises who develop recommendation systems.

Also, would be good if you show how your models/system compare to other solutions.