Skip to content
NTPU AI Learn

DS 201 Apply

Turn what you learned into your own Predictive Analytics Use Case + Model Card

What this final artifact is for

The Predictive Analytics Use Case + Model Card is the final artifact of DS 201. Choose a real prediction problem you face, build a baseline and a model, and clearly write the problem, audience, data, method, verification, evidence, limitations, risk and governance, the human reviewer, and the next step. This becomes the starting point for later practice discussion and deployment decisions.

Info

Human, AI, Human: a person defines the problem and the audience; AI may help write code or draft the narrative; a person verifies the evidence, claims, and deployment decision, and remains responsible for the result.

What to fill in

  • Problem, audience, and data (source, grain, time coverage, key definitions)
  • Method and workflow
  • At least three verification checks
  • Evidence and output: what the model or workflow actually produced
  • Limitations
  • Risk and governance considerations (cost, drift, monitoring, human fallback)
  • The human reviewer
  • Next step

A well-structured Predictive Analytics Use Case + Model Card

A well-structured artifact includes a clear, checkable problem, a clearly stated data source and grain, a reproducible method, at least three verification checks, evidence and claims consistent with the observed model performance and baseline comparison, and at least one limitation.

Info

The platform does not automatically judge whether your model or deployment decision is correct. This artifact is used for learning feedback and later discussion, and is reviewed by a person.

Exit Ticket

Finally, use the Exit Ticket to record today's most important idea, the step you are still unsure about, where you would apply this method in a real context, the risk you most need to verify, and your difficulty and usefulness ratings.

Before you submit

Warning

Do not enter company secrets, client data, personal data, or other unauthorized sensitive information. Unless authorized, never upload confidential institutional or company data to an AI tool; check your institution's policy before working with real operational data.

Go to the forms

What you need to complete

  • Complete both DS 201 modules
  • Score at least 80% on the course post-test
  • To earn the Predictive Analytics Capability Certificate, also submit a Predictive Analytics Use Case + Model Card and have it reviewed by a Credential Admin against the rubric

How you are assessed

A Credential Admin scores the Predictive Analytics Use Case + Model Card across seven weighted domains: Problem & Decision Framing, Data Source & Grain, Method & Reproducibility, Verification Rigor, Evidence vs. Baseline Claim, Limitations/Risk & Governance, and Human Review & Next Step. Out of 21 points, 17 or more with no critical-fail rule triggered is a PASS; 13 or fewer, or any triggered critical-fail rule, is a FAIL.

Info

This scoring logic is public so you know what is being assessed. It is not the same as quiz answer keys, and it is a different, human-reviewed pass from the automated reference score you already see on the page -- the Credential Admin makes the final call.

What counts as evidence

  • A recorded rubric result (PASS, REVISION_REQUIRED, or FAIL) with no critical-fail rule triggered
  • A PASS leaves individual capability evidence for all eight DS 201 fine-grained competencies (Prediction Problem Framing; Baseline Comparison; Split Integrity & Leakage Detection; Regression Evaluation; Classification, Precision/Recall & Threshold; Overfitting, Cross-Validation & Tuning; Feature Importance & Fairness; Error Analysis, Drift & Deployment Judgment)

What you can earn

DS 201 Course Completion Certificate: complete both modules and reach the post-test threshold -- no Predictive Analytics Use Case + Model Card required. Predictive Analytics Capability Certificate: also requires a submitted Predictive Analytics Use Case + Model Card that passes rubric review. The two are earned independently of each other.

What this does not mean

This credential confirms the holder completed DS 201's required coursework and post-test, or (for the capability certificate) demonstrated target/baseline judgment, split and leakage checking, model evaluation, verification, and human-review design on the Predictive Analytics Use Case + Model Card.

  • It does not represent a formal data-science or machine-learning professional license or hiring qualification
  • It does not mean any specific predictive model or deployment decision the holder makes later will necessarily be correct
  • It does not mean human review can be skipped before a high-risk action (Human, AI, Human)

What next?