Skills101
← All practice quizzes

Quiz: Classification

5 questionsNo time limitPass: 60%+10 XP on first pass

Predict categories (placed or not, fraud or genuine) with logistic regression and decision trees, read a confusion matrix, and choose between accuracy, precision and recall — with a placement-prediction case study and an imbalanced-data trap.

Log in to take the quiz

Free account · see your score, answers and explanations, earn XP

  1. Question 1

    A fraud model flags 100 transactions; 20 are really fraud. What is its precision?

  2. Question 2

    There are 50 at-risk students; the model flags 40 of them correctly. What is the recall?

  3. Question 3

    What happens when you lower the classification threshold from 0.5 to 0.3?

  4. Question 4

    Only 1% of emails are spam. A model that predicts "not spam" for everything has what accuracy?

  5. Question 5

    What does stratify=y do in train_test_split?