When a user question matches an intent that it’s been train! on in the chatbot model, the NLP provider returns the intent with a confidence score as a percentage (in fact, NLP providers will typically return up to ten possible intent pr!ictions in order of decreasing confidence score).
This percentage represents how confident the NLP
Cyara’s conversational AI optimization solution helps businesses accelerate chatbot development and assure CX at scale.
But what if the highest intent pr!iction is only 25% confident? You wouldn’t want a user to bulk sms indonesia be present! with an intent answer when the chatbot model is not very confident of this pr!iction. This is where the confidence threshold comes in.
If a confidence threshold is set in the model, its function is to only present the user with what is a webinar? the top pr!ict! intent if the confidence of that pr!iction is above the set threshold.
Then if the top pr!ict! intent falls below this threshold, the user will be present! with the fallback answer, “I’m sorry, I don’t understand” (or something similar), or hand! over to a human agent for assistance.
What Level Do You Set Your Confidence Threshold to?
A typical threshold may be set to a default level of 50%, and this threshold may or may not work for your chatbot.
If you are risk adverse, you may want to set the confidence threshold higher australia data to minimize the risk of incorrect answers to your users.
However, the downside of this would be the potential for your chatbot to give too many fallback answers (or being pass! to a human agent too frequently, thus defeating the object of having a chatbot!) – even if the intent was correct and with reasonably high confidence.
Conversely, you might be comfortable with a little bit of risk and so you’ll want to set your confidence threshold lower to maximise the correct answers to your users.
But consequently, the number of incorrect responses could potentially be higher.
So, there could be a little bit of a trial-and-error process of finding out what works best for your chatbot, through constant testing and re-adjusting of the threshold level.
“