Module 13 · Responsible systems

Module 13: guided construction and mastery

Use this after the foundation bridge and before attempting independent practice; return to the module run instructions afterward. Read, predict, run, change, and explain. The shared runner remains the complete reference; these small steps expose its ideas.

Worked concept

In an illustrative group with 20 positives and 15 true positives, TPR is .75. If a second group has 4 positives and 3 true positives, its TPR is also .75 but based on much less evidence. A metric cannot establish that predicting historical income is a legitimate decision.

Predict and construct

Predict the printed values, shape or rejection before running. Use the documented environment. The notebook contains this same runnable construction cell.

from practical_ml_ai.learning import wilson_interval
for learning_successes,learning_n in [(15,20),(3,4)]:
    print("rate",learning_successes/learning_n,"illustrative interval",wilson_interval(learning_successes,learning_n))
assert wilson_interval(3,4)[1]-wilson_interval(3,4)[0] > wilson_interval(15,20)[1]-wilson_interval(15,20)[0]

Complete with less support

Reconcile two real group rates and denominators. Explain the historical label and an intersectional limitation. Demonstrate uncertainty arithmetic while stating dependence and sampling assumptions.

Debug a plausible misconception

Does removing protected columns remove bias? Write a prediction before opening feedback. Include a counterexample or calculation, not only a definition.

Independent transfer

Write a stakeholder recommendation that includes a reason not to deploy; distinguish a normative judgment from an observed rate.

Minimum mastery evidence

Keep the evidence listed in the study workflow and name the module outcome each item supports. The criteria describe developing, meeting and extending the outcome.