From the course: Microsoft Power Apps: AI Builder

Unlock the full course today

Join today to access over 22,600 courses taught by industry experts or purchase this course individually.

Evaluate and manage the classification model

Evaluate and manage the classification model - PowerApps Tutorial

From the course: Microsoft Power Apps: AI Builder

Start my 1-month free trial

Evaluate and manage the classification model

- [Instructor] After the model has been trained and we've dismissed the dialogue box, we end up back here on the models page with some information about the performance. The score here of 66 we see is a score between one and 100. I'd be hoping for something a little higher, but remember that if we have a super high score like 97, it probably means, as it did with the object detection model, that we don't have as large of a data set as we might have, and we didn't have enough diversity in the data set that we were using for training. Here, when we have this low of a score, it's really exactly the same thing. The category classification model would like us to give it 1,000 rows of data that's already tagged. We gave it fewer than 50. So, it doesn't have as much confidence in what it's telling us. But, let's do a quick test. You'll find some testing information in the category classification testing spreadsheet. For…

Contents