Scribd
Upload
123 views

Final Assessment Data Mining

1. The document is a final assessment exam for an elective course on data mining. It contains 10 questions assessing various data mining concepts and algorithms. 2. The questions cover topics like distance measures, similarity measures, classification tasks, decision trees, naive Bayes, k-nearest neighbors, rule-based classifiers, association rule mining, and frequent pattern growth. 3. Students are instructed to show their work, answer all questions, and cite their student identification number with their responses.

Uploaded by

सुजन कार्की
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
123 views

Final Assessment Data Mining

1. The document is a final assessment exam for an elective course on data mining. It contains 10 questions assessing various data mining concepts and algorithms. 2. The questions cover topics like distance measures, similarity measures, classification tasks, decision trees, naive Bayes, k-nearest neighbors, rule-based classifiers, association rule mining, and frequent pattern growth. 3. Students are instructed to show their work, answer all questions, and cite their student identification number with their responses.

Uploaded by

सुजन कार्की
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

SAGARMATHA ENGINEERING Exam Final Assessment

COLLEGE Level BE Full marks 40


(Tribhuvan University Affiliated) Program BCT Pass marks 16
Sanepa, Lalitpur, Nepal Year/Part IV/I Time 1.5hr
(2078, Shrawan)

Subject: Elective I: Data Mining (CT 725 02)

 Give your answers in your own words as far as practicable.


 All questions carry equal marks.
 (R: Your class roll no)
 Attempt All Question.
1. Create the dissimilarity matrix for given data points using the Euclidean and Supremum
distance measure techniques. [3]
Point Attribute 1 Attribute 2
P1 R 10
P2 R+5 20
P3 R*2 30
2. For what kind of data Cosine similarity is used? Find the cosine similarity for
D1=[R,4,0,2,1] and D2= [R+6,0,0,6,3]. [1.5]
3. Find the SMC and Jaccard coefficient for a1=[11001] and a2=[10100] [1]
4. What do you understand by classification task? How supervised learning is implemented
on classification task? [2.5]
5. How greedy approach is implemented on decision tree algorithm. Explain with the suitable
example. How will you handle overfitting problem in decision tree [5+2]
6. What are the basic assumption on naïve Bayes? How it is differ from Bayesian Belief
Networks? If a person doesn’t do exercise, he is also not taking he healthy diet, if he got
the chest pain but no the blood pressure then determine whether the person has heart disease
or not. [1.5+1.5+3]

Exercise=Yes 0.7 Diet=Healthy 0.25


Exercise=No 0.3 Diet=Unhealthy 0.75

Exercise Diet

D=Healthy D=Healthy D=Unhealthy D=Unhealthy


Heart E=Yes E=No E=Yes E=No
Disease HD=Yes 0.25 0.45 0.55 0.75
HD=No 0.75 0.55 0.45 0.25

Blood
Chest Pain
Pressure

HD=Yes HD=No HD=Yes HD=No


CP=Yes 0.8 0.01 BP=High 0.85 0.2
CP=No 0.2 0.99 BP=Low 0.15 0.8
7. Why KNN is known as lazy learning algorithm? Explain the working of ANN with the
suitable example. [5]
8. How will you get the conflict on rule based classifier? What strategy will you implement
to manage the conflict? [4]
9. What are the role of support and confidence in association analysis? Find all strong
associations rule for the frequent itemset with support and confidence 50% for the
following transaction. [5]
TID Items
1 ACD
2 BDE
3 ABCD
4 EDF
10. Explain FP growth algorithm. Compute all the conditional pattern for following
transactions using the FP growth algorithm. (Take_min_support 3)
[5]
TID Items brought
100 {M, O, N, K, E, Y}
200 {D, O, N, K, E, Y}
300 {M, A, K, E}
400 {M, U, C, K, Y}
500 {C, O, O, K, I, E}

……..😃…….

You might also like