Table of Contents

Testing Process

John Cordeiro Updated by John Cordeiro

The test functionality in Bothub was created to evaluate your Training data in a automatic way. Users can add sentences that's outside the training data to evaluate the quality of the training data or algorithm selected.

Precision and recall reports

A perfect precision score of 1.0 means that every test result was positive (but says nothing about whether all positive results were retrieved) whereas a perfect recall score of 1.0 means that all positive results were retrieved by the search (but says nothing about how many false positives were also retrieved).

Intent confusion matrix

The confusion matrix shows you which intents are mistaken for others.

Intent confidence distribution

The histogram allows you to visualize the confidence distribution for all predictions, with the volume of correct and incorrect predictions being displayed by green and red bars respectively. Improving the quality of your training data will move the green histogram bars to the right and the red histogram bars to the left of the plot.

How did we do?


Integration (Push)