Oracle Cloud Infrastructure Data Science Professional: Hands-On Workshop — Lesson 4: Model Deployment, Endpoints, Monitoring, MLOps, and Responsible Operation

Learning Objectives

• Explain the purpose and operating context of model artifacts, runtime environments, deployments, endpoints, and scaling.
• Apply request schemas, batch versus online inference, testing, and rollback and logs, metrics, latency, drift indicators, failures, and alarms in a controlled environment.
• Validate outcomes and troubleshoot risks involving pipelines, retraining, governance, documentation, and model runbook.

Detailed Topics

• model artifacts, runtime environments, deployments, endpoints, and scaling
• request schemas, batch versus online inference, testing, and rollback
• logs, metrics, latency, drift indicators, failures, and alarms
• pipelines, retraining, governance, documentation, and model runbook

Instructor Demonstration

Demonstrate model artifacts, runtime environments, deployments, endpoints, and scaling for a customer-churn model developed in OCI Data Science and promoted through a controlled deployment; capture the exact configuration, code, command, transaction, query, dashboard, model, schedule, or report evidence that proves the expected result.

Hands-On Exercise

Complete a controlled Oracle Cloud Infrastructure Data Science Professional: Hands-On Workshop exercise covering request schemas, batch versus online inference, testing, and rollback and logs, metrics, latency, drift indicators, failures, and alarms; introduce an exception involving pipelines, retraining, governance, documentation, and model runbook, diagnose it from evidence, apply the smallest reversible correction, and rerun acceptance checks.

1. Confirm scope, prerequisites, identities, dependencies, data, risks, and expected outcome.
2. Perform the course-specific configuration, development, administration, analysis, or business-process workflow.
3. Capture commands, settings, records, logs, screenshots, reports, metrics, or test results.
4. Compare the observed result with acceptance criteria and document corrective or preventive action.

Scenario Analysis

• Identify the technical or business decision and the stakeholders affected by it.
• Compare security, performance, reliability, compliance, cost, usability, and support trade-offs.
• Define rollback, recovery, communication, evidence, ownership, and escalation requirements.

Troubleshooting Guidance

Diagnose issues involving model artifacts, runtime environments, deployments, endpoints, and scaling, request schemas, batch versus online inference, testing, and rollback, logs, metrics, latency, drift indicators, failures, and alarms, pipelines, retraining, governance, documentation, and model runbook without making an unverified production change. Separate symptoms from causes, gather time-correlated evidence, test a reversible hypothesis, validate the correction, and record recurrence controls.

Validation Checklist

• The requirement, environment, inputs, dependencies, and expected result are documented.
• The result is reproducible and supported by product-specific evidence.
• Normal, boundary, failure, security, performance, and operational conditions are reviewed.
• Exceptions, rollback, ownership, support actions, and the next improvement priority are recorded.

Lesson Outcome

Learners can apply Model Deployment, Endpoints, Monitoring, MLOps, and Responsible Operation in a realistic Oracle Cloud Infrastructure Data Science Professional: Hands-On Workshop scenario and defend the result with documented evidence.