Microsoft Azure AI Fundamentals (AI-900)Describe fundamental principles of machine learning on AzureMedium
A team is developing a machine learning model to predict whether a customer will click on an advertisement. They have collected data including customer demographics, past browsing history, and ad features. The output of the model will be a 'yes' or 'no' decision (click or no click). What type of machine learning task is this, and what kind of target variable does it have?
- AClassification; categorical discrete
- BReinforcement Learning; reward signal
- CClustering; no target variable
- DRegression; continuous numerical
Show answer & explanationAnswer & explanation
Correct answer: A. Classification; categorical discrete
Predicting a 'yes' or 'no' outcome falls under classification, as it involves assigning data points to predefined discrete categories. The target variable is inherently categorical and discrete.
Why the other options are wrong
- B. Reinforcement learning involves an agent learning through rewards in an environment, not directly predicting a 'yes/no' outcome from labeled data.
- C. Clustering is an unsupervised task without a predefined target variable.
- D. Regression predicts continuous numerical values, not discrete categories.
Classification
A supervised machine learning task that involves predicting a discrete class label for a given input data point.
- Output is a category (e.g., spam/not spam, disease/no disease).
- Requires labeled training data with discrete target values.
- Can be binary (two classes) or multi-class (more than two classes).
Memory trick: Supervised: Predict Category or Quantity