The Total Automation vs. Error graphs show the relationship between the automation rate and error rates for all categories in the knowledge base. Use these graphs to evaluate the performance of your knowledge base and find the right balance between automation rate and error rate.
The percentage of your content that is classified automatically is referred to as the automation rate. While ideally you want to automatically classify all of your content, there might be some errors along the way. For example, some content items might receive scores that exceed the threshold of a category in the knowledge base, even if they do not belong to that category.
The percentage of content that is automated incorrectly is referred to as the error rate. The higher the threshold is set for a category, the lower the error rate will be. This is because only documents that receive high scores for the category will be classified automatically. However, setting a higher threshold also means that a lower percentage of documents will be classified automatically.
Suppose a document should be classified into a category called Sales. If the document is classified into the Marketing category instead of the Sales category, this is clearly a classification error. But what if the document is correctly classified into the Sales category and also belongs in the Marketing category? Depending on your classification requirements, this may or may not be considered a error.
Find the point on the graph that best fits your business requirements. In most cases you want to find the point that provides the highest possible automation rate with the lowest acceptable error rate. For example, an organization that can accept a 5% error rate might find that this corresponds to a 90% automation rate.
You can use the strict error rate to set thresholds for categories in your knowledge base. For more information, see the topic on setting thresholds.