Start with a Prediction
Which components need inspection?
A score of 0.5 can still trigger inspection
The component model supplies a score, while the inspection rule expects a failure probability. Botie must keep those two quantities distinct.
BOTIE
The inputs we are comparing
Component failure score
Example 1
-2
Example 3
0.5
Result for example 1
0
A positive score just below the action boundary
This check uses the pieces from “Make the inspection decision after conversion”.
BOTIE
- Component failure score
0.4
Use a number, text, or an array matching the requested result. For a matrix, put each row in brackets. Saving your prediction runs your current construction on these inputs and checks the earlier examples too.
Build a construction in the workspace above first. This case will test those pieces.
Where could you change the inspection policy while leaving the score-to-probability conversion intact?
Separate a model's numeric score, its probability interpretation and the decision made from that probability.
This is a small construction problem. The lesson explains the assumptions and the parts of the full method that this example leaves out.
Work through the Python challenges →