Is your feature request related to a problem? Please describe.
Not a problem. But it is important to understand and use Feature Importance calculation to see if a Feature (Decision Point) is useful and helps actually make a decision valuable. If the value is miniscule, it can be eliminated entirely. There is potential for understanding the cost in collecting the information (for the Feature/decision point) that could be also disproportional - we should avoid these type of decision points if the decision can be made easier.
Describe the solution you'd like
Would like documentation with examples to show how Feature Importance can be calculated for a decision table. When a decision point is of small value, it can be removed. A full simple example may help people deciding to build their own decision tables be able to find ways to eliminate decision points that are of very low value or no value.
Is your feature request related to a problem? Please describe.
Not a problem. But it is important to understand and use Feature Importance calculation to see if a Feature (Decision Point) is useful and helps actually make a decision valuable. If the value is miniscule, it can be eliminated entirely. There is potential for understanding the cost in collecting the information (for the Feature/decision point) that could be also disproportional - we should avoid these type of decision points if the decision can be made easier.
Describe the solution you'd like
Would like documentation with examples to show how Feature Importance can be calculated for a decision table. When a decision point is of small value, it can be removed. A full simple example may help people deciding to build their own decision tables be able to find ways to eliminate decision points that are of very low value or no value.