Understand machine learning problems
Connect examples, features, labels, and objectives to the kind of problem you want to solve.
- Distinguish supervised and unsupervised learning and identify a prediction target.
Machine learning (ML) uses data to fit a model that can make predictions or find patterns. In supervised learning, examples include a target label or value: classification predicts categories, while regression predicts numeric values. Unsupervised learning looks for structure without a provided target, such as groups or lower-dimensional representations. Start by defining the real task and what a useful result means.
A small example
1features = {"rooms": 3, "area_m2": 82}
2label = 275000 # observed sale price
3print("features:", features)
4print("target:", label)features: {'rooms': 3, 'area_m2': 82}
target: 275000A model learns patterns in the training examples, not the meaning of the task by itself. The target must be measured consistently and available at the time a prediction is made. A dataset’s patterns may reflect collection choices or historical bias rather than stable relationships.
Key takeaways
Distinguish supervised and unsupervised learning and identify a prediction target.
Evaluate on relevant unseen data and monitor the system after deployment.
Lesson quiz
5 questions · pass with 4 correct · up to 50 XP
Passing this quiz completes the lesson and keeps your streak going. Questions you miss come back in review sessions later.
Questions about this lesson
Stuck? Ask. Figured something out? Share it. Explaining is one of the best ways to learn.
Loading posts…