model selection

Choosing a model by first rejecting candidates that break hard limits, then weighing the rest on quality, latency and cost measured on your own tasks.

In more detail

Hard filters such as licence, data residency and required features are applied before any scoring, so a good score can never outvote them. Record the decision in a rerunnable file, because new models, prices and deprecations will force you to choose again.

Related terms

Taught in

References

Certification courses