GLOSSARY
What is a decision model in AI?
Decision modelA decision model (in AI, an AI decision model) maps an input to an answer from a known set, with a probability for each answer, instead of producing open-ended text. System One models are decision models that take their questions at run time.
Classifiers are the oldest decision models: a fixed set of labels, trained once. What System One models add is that the questions and their allowed answers arrive with each request. The same model can route a support ticket on one call and score a sales lead on the next, with no retraining.
Because the output is a distribution over known answers, a decision model is evaluated the way a classifier is (accuracy, calibration, latency) rather than by judging prose.
The same models go by several names: AI decision models, typed decision models, System One (or System 1) models, and, after the first one, Jev-style models. In business analytics "decision model" also means a decision table or a DMN diagram; this glossary means the machine-learning kind.
Read more
Next term: System One model registry · Every System One model