🧠 UNIT III – Classification (Important Questions)
1. What is classification? How does it differ from clustering?
2. Explain the working and construction of a Decision Tree with example.
3. What are attribute selection measures? Explain Information Gain, Gain Ratio, and
Gini Index.
4. What is tree pruning? Explain pre-pruning and post-pruning.
5. Explain Rule-Based Classification using IF–THEN rules with example.
6. Explain Bayes’ Theorem and its use in classification.
7. What is Naive Bayes Classifier? Explain its working with a suitable example.
8. What is a Bayesian Network? How is it different from Naive Bayes?
9. Explain the working of a Perceptron with neat diagram.
10. Explain the working of k-Nearest Neighbor (k-NN) classifier with example.
11. What is a Support Vector Machine (SVM)? Explain its working with diagram.
12. Differentiate between Linear and Non-Linear SVM.
13. What is Linear Regression? Explain with example and formula.
14. Differentiate between Linear and Non-Linear Regression.
15. What is Prediction? How does it differ from classification?
🧠 UNIT IV – Clustering & Association Rule Mining
(Important Questions)
1. What is clustering? Explain its applications and requirements.
2. Explain Agglomerative Hierarchical Clustering with example and diagram.
3. Explain Divisive Hierarchical Clustering.
4. Explain the k-Means algorithm with step-by-step example.
5. Explain the k-Medoids algorithm and compare it with k-Means.
6. What is Association Rule Mining? Define support, confidence, and lift.
7. What is Market Basket Analysis? Give an example.
8. Explain Apriori Algorithm with suitable example.
9. What is the Apriori property?
10. Explain Multilevel Association Rules with example.
11. What is Constraint-Based Association Rule Mining?
🧠 UNIT III – Classification (Important Questions with
Examples)
1. What is classification? How does it differ from clustering?
Example: Classifying emails as Spam or Not Spam based on content.
(Clustering groups similar data without predefined labels.)
2. Explain the construction of a Decision Tree with an example.
Example:
Outlook Temperature Humidity Wind PlayTennis
Sunny Hot High Weak No
Overcast Hot Normal Strong Yes
Tree built using Information Gain → root = Outlook → branches decide PlayTennis.
3. What are attribute selection measures? Explain Information Gain, Gain Ratio,
and Gini Index.
Example:
Using “Outlook” gives highest Information Gain for “PlayTennis” dataset.
4. What is Tree Pruning? Explain Pre-Pruning and Post-Pruning.
Example: Removing unnecessary branches of a decision tree to avoid overfitting.
5. Explain Rule-Based Classification using IF–THEN rules with example.
Example:
IF Outlook = Sunny AND Humidity = High THEN PlayTennis = No
IF Outlook = Overcast THEN PlayTennis = Yes
6. Explain Bayes’ Theorem with example.
Formula:
P(H|X) = [P(X|H) × P(H)] / P(X)
Example:
If 80% of emails are not spam and 10% of spam mails contain “Free”, find probability of spam
when “Free” appears.
7. Explain Naive Bayes Classifier with example.
Example:
Predict whether a student will pass based on study hours and attendance using Naive Bayes
probabilities.
8. What is a Bayesian Network?
Example:
Nodes: Weather → Traffic → LateForOffice
Shows dependency: Weather affects Traffic, which affects LateForOffice.
9. Explain the working of a Perceptron with diagram.
Example:
Inputs x₁=2, x₂=3; weights w₁=0.4, w₂=0.3 → weighted sum = (2×0.4)+(3×0.3)=1.7
If 1.7>threshold, output = 1 (class A).
10. Explain k-Nearest Neighbor (k-NN) algorithm with example.
Example:
Classify a new point based on 3 nearest points using Euclidean distance.
If 2 neighbors are “Yes” and 1 is “No” → predict “Yes”.
11. Explain Support Vector Machine (SVM) with example.
Example:
In a 2D plot of “Exam Marks” vs “Attendance,” SVM finds a line that best separates Pass and
Fail students with maximum margin.
12. Differentiate between Linear and Non-linear SVM.
Example:
Linear – data separable by a straight line.
Non-linear – data separable using kernel functions (like polynomial or RBF).
13. Explain Linear Regression with example.
Equation: y = a + bx
Example:
Predict House Price (y) from Area (x):
y = 50,000 + 1000x → if x = 100 → price = ₹1,50,000.
14. Explain Non-Linear Regression with example.
Example:
Growth of bacteria follows exponential curve → y = ae^(bx).
15. What is Prediction? How does it differ from classification?
Example:
Classification → predict label (Pass/Fail).
Prediction → predict numeric value (marks = 85).
🧠 UNIT IV – Clustering & Association Rule Mining
(Important Questions with Examples)
1. What is Clustering?
Example:
Grouping customers into clusters like High Spenders, Moderate Spenders, Low Spenders.
2. Explain Agglomerative Hierarchical Clustering with example.
Example:
Start with each object as a separate cluster, then merge closest pairs until one cluster remains →
shown as dendrogram.
3. Explain Divisive Hierarchical Clustering.
Example:
Start with one big cluster and recursively split it until each object is separate.
4. Explain k-Means Algorithm with step-by-step example.
Example:
Given points (1,1), (1.5,2), (5,8), (8,8).
k=2 → choose centroids → assign points → update centroids → repeat until stable.
5. Explain k-Medoids Algorithm and differentiate it from k-Means.
Example:
k-Medoids chooses actual data points as centers → more robust to outliers than k-Means.
6. What is Association Rule Mining? Define support, confidence, and lift.
Example:
Rule: {Bread} → {Butter}
Support = 40% (both together in 40% transactions)
Confidence = 80% (if Bread, then Butter 80% times)
Lift = 1.6 (strong positive association)
7. What is Market Basket Analysis?
Example:
People who buy Milk often buy Bread → helps in store layout and promotions.
8. Explain Apriori Algorithm with example.
Example:
Transactions:
T1: {Milk, Bread, Butter}
T2: {Milk, Bread}
T3: {Bread, Butter}
Frequent itemsets found using min support → generate rules like {Milk} → {Bread}.
9. What is the Apriori Property?
Example:
If {Milk, Bread} is frequent, then {Milk} and {Bread} must also be frequent.
10. Explain Multilevel Association Rules with example.
Example:
Electronics → Laptop → Dell Laptop
Rule: {Electronics} → {Dell Laptop} (multilevel association).
11. What is Constraint-Based Association Rule Mining?
Example:
Find rules only for food items or for items with support > 50%.