The RapidMiner community is on read-only mode until further notice. Technical support via cases will continue to work as is. For any urgent licensing related requests from Students/Faculty members, please use the Altair academic forum here.
Can confidence value for prediction be interchangeably be used with the likelihood for an event?
![bhawnath131](https://us.v-cdn.net/6030995/uploads/defaultavatar/nCCNNSPK1YM69.jpg)
![](https://s3.amazonaws.com/rapidminer.community/vanilla-rank-images/newbie-16x16.png )
For example: 0.978 confidence (yes) can be implied as the likelihood (chances) of this event being true is 97.8%.
![Image: https://us.v-cdn.net/6030995/uploads/editor/xc/sdszm4135ztr.png](https://us.v-cdn.net/6030995/uploads/editor/xc/sdszm4135ztr.png)
0
Best Answer
-
rjones13 Member Posts: 191
Unicorn
Hi @bhawnath131,
Confidence when training machine learning and testing performance can be more thought of as an indicator of how sure the model is for that set of values. For example, if it has a confidence of 0.97 for a class, then it's very sure in that classification. The way confidence is calculated depends on the algorithm used.
Hope this helps.
Best,
Roland0