Oracle Cloud Infrastructure Data Science Professional (2025): Hands-on Workshop — Lesson 3: Model catalog, metadata, artifacts, model deployments, endpoints, scaling, authentication, testing, and prediction integration

Learning Objectives

• Assess the dependencies, controls, and expected business outcome for Model catalog, metadata, artifacts, model deployments, endpoints, scaling, authentication, testing, and prediction integration.
• Demonstrate the workflow and leave reproducible evidence in registered model and endpoint validation trace.
• Recommend a preventive improvement after resolving a deployment returning valid responses with an incorrect feature order.

Detailed Topics

• Model catalog
• Metadata
• Artifacts
• Model deployments
• Endpoints
• Scaling
• Authentication
• Testing
• And prediction integration
• Decision ownership, prerequisites, and acceptance evidence for Model catalog, metadata, artifacts, model deployments, endpoints, scaling, authentication, testing, and prediction integration
• Relevant access, data, integration, performance, recovery, and support considerations

Instructor Demonstration

The instructor builds a representative scenario for Model catalog, metadata, artifacts, model deployments, endpoints, scaling, authentication, testing, and prediction integration, narrating each decision and showing how it contributes to a reproducible OCI Data Science workflow that prepares data, trains and deploys models, automates lifecycle tasks, and monitors business-facing predictions. The demonstration records registered model and endpoint validation trace so learners can compare configuration intent with observable behaviour.

Hands-On Exercise

Complete a guided task covering Model catalog, metadata, artifacts, model deployments, endpoints, scaling, authentication, testing, and prediction integration. After establishing a working baseline, reproduce “a deployment returning valid responses with an incorrect feature order,” isolate the responsible setting or data condition, apply a reversible fix, and update registered model and endpoint validation trace with before-and-after proof.

1. Map the current process and mark where the expected result can first be observed.
2. Run the scenario while preserving timestamps, job identifiers, and relevant output.
3. Apply a reversible correction only after evidence supports the cause.
4. Retest the original case plus an unaffected case and update the handover record.

Scenario Analysis

• Clarify the business trigger, affected roles, required records, and acceptable result for Model catalog, metadata, artifacts, model deployments, endpoints, scaling, authentication, testing, and prediction integration.
• Compare at least two implementation or correction choices and identify which evidence would distinguish them.
• Decide how registered model and endpoint validation trace should be reviewed, approved, retained, and handed to the next owner.

Troubleshooting Guidance

For a failure in Model catalog, metadata, artifacts, model deployments, endpoints, scaling, authentication, testing, and prediction integration, separate access, setup, data, integration, and timing causes. Compare the observed sequence with registered model and endpoint validation trace; if “a deployment returning valid responses with an incorrect feature order” is confirmed, make the smallest reversible correction and document why broader changes were rejected.

Validation Checklist

• Prerequisites and role permissions for Model catalog, metadata, artifacts, model deployments, endpoints, scaling, authentication, testing, and prediction integration have been confirmed before execution.
• The result agrees with the expected values documented in registered model and endpoint validation trace.
• Exceptions are explained with evidence rather than hidden by manual correction.
• The final record names the approver, monitoring point, and next improvement action.

Lesson Outcome

Learners can apply Model catalog, metadata, artifacts, model deployments, endpoints, scaling, authentication, testing, and prediction integration, explain the decisions made, and defend the result with registered model and endpoint validation trace.