Artificial Intelligence (417) — CBSE Class 10 board question

(a) Clustering (2 marks)

Clustering is an unsupervised learning model that groups unlabeled data into clusters based on similarities or patterns identified by the machine.

• The model finds similar data points and places them in the same cluster, differentiating them from objects in other clusters.
• No predefined class labels are given; the machine discovers groups on its own.
• Example: A supermarket customer database is clustered into "grocery shoppers" and "non-grocery shoppers" without any prior labels. OTT platforms like Netflix use clustering for recommendations.

(b) Dimensionality Reduction (2 marks)

Dimensionality Reduction is an unsupervised learning technique used to reduce the number of features (dimensions) in a dataset while retaining important patterns and relationships.

• It helps simplify large, complex datasets, making them easier to process and visualize.
• It removes redundant or irrelevant features, improving model efficiency.
• Example: Compressing pixel data of images while preserving key features for pattern recognition.

Source: Chapter 2, Section 2.2 – Sub-categories of Unsupervised Learning Model

---

• Clustering is directly covered in the source passages with examples — always mention it is unsupervised and uses unlabeled data. Examiners expect the distinction from classification (no predefined labels).
• Dimensionality Reduction is listed as a sub-category of unsupervised learning models but not elaborated in the passages — give a definition + purpose + example for full marks.
• The key examiner expectation: link both to unsupervised learning and unlabeled data.