Compare the characteristics and capabilities of the two types of custom models below:

Model type        | Characteristics | Capabilities
------------------|-----------------|--------------
Structured        | <ul><li>Uses a target type known to DataRobot (e.g., regression, binary classification, multiclass, and anomaly detection).</li><li>Required to conform to a request/response schema.</li><li>Accepts [structured input and output data](structured-custom-models#structured-custom-model-requirements).</li></ul> | <ul><li>Full deployment capabilities.</li><li>Accepts training data after deployment.</li></ul>
Unstructured      | <ul><li>Uses a custom target type, unknown to DataRobot.</li><li>Not required to conform to a request/response schema.</li><li>Accepts unstructured input and output data.</li></ul> | <ul><li>Limited deployment capabilities. Doesn't support data drift and accuracy statistics, challenger models, or humility rules.</li><li>Doesn't accept training data after deployment.</li></ul>