Classification Machine Learning Scenarios Quiz

5 questions Pass: 70% +25 pts (50 with Pro)

Quiz covering Machine Learning Techniques

What you'll be asked

  1. Which of the following scenarios is a classic example of a binary classification problem in Machine Learning?
  2. You are building a model in Azure Machine Learning to categorize customer support tickets into one of four departments: Billing, Technical, Shipping, or General Inquiry. Which metric is most appropriate for evaluating this multi-class classification model?
  3. A bank uses a machine learning model to detect fraudulent credit card transactions. Because fraud is rare, the dataset is highly imbalanced (99% legitimate, 1% fraudulent). Why might 'Accuracy' be a misleading metric for this model?
  4. When configuring an Automated Machine Learning (AutoML) job in Azure to perform classification, what is the purpose of the 'Primary Metric' setting?
  5. You are evaluating a classification model using a Confusion Matrix. The model predicts 'Positive' for 50 cases, but 10 of those were actually 'Negative'. The model predicts 'Negative' for 100 cases, but 5 of those were actually 'Positive'. What is the Precision of your model?

Answers and explanations come after you submit.