Skip to content

Machine Learning

CSE · Quiz · Fall 26

Paper 3 of 3Section C · Batch 65 · SUPAN ROY (2)Switch

Section C · Batch 65

Paper 3 of 3

This browser can’t show the PDF here

Open it, and your phone’s PDF viewer takes it, or download it.

Read the questions as text

Read off the PDF by AI, so it may have mistakes. The PDF is the original.

CT-2 CSE 431 Machine Learning (Sec-C) Total Marks: 15 Time: 30 Minutes 1. A digital streaming company wants to predict whether a visitor will purchase a premium subscription after viewing advertisements. The dataset includes the following information: ID | Age Group | Monthly Income | Ad Viewing Time (Minutes) | Purchase Premium 1 | Young | High | 12 | Yes 2 | Young | Low | 5 | No 3 | Young | Low | 8 | No 4 | Adult | High | 15 | Yes 5 | Adult | Low | 10 | Yes 6 | Adult | High | 18 | Yes a) Calculate the entropy of the parent dataset. b) Split the dataset using Age Group and calculate the entropy of each child node, weighted entropy, and information gain. c) Consider the numerical attribute Ad Viewing Time. Use a threshold of 9 minutes to divide the dataset into two groups (≤ 9 minutes and > 9 minutes). Calculate the entropy of each child node, weighted entropy, and information gain. d) Compare the information gains of Age Group and Ad Viewing Time. Which attribute should be selected as the root node? Justify your answer.