Every PRO System has a number of qualifications to take a look at: record, winning percentage and ROI to name a few. You'll also notice that there is a letter grade attached to each system, too.
The grade is a report card that tells you the strength of the system based on two major factors:
- ROI Score (ZScore): A statistical measure that tells you how above or below average the results of your system would be given the sample size of your system.
- Overfitting Score (Too many selected items/filters): Overfitting occurs when the system describes random error or noise instead of the underlying relationship. This happens when a model is excessively complex, such as having too many parameters relative to the number of observations. A model which has been overfit will generally have poor predictive performance, as it can exaggerate minor fluctuations in the data.
Most PRO Systems will have an 'A' as a grade, but won't always be the case.