Tribhuvan University
Bachelor of Science in Computer Science and Information Technology
Semester 7 · Model question
Course Title: Data Warehousing and Data Mining (CSC410)
Full Marks: 60Pass Marks: 24Time: 3 hours
Candidates are required to give their answers in their own words as far as practicable. The figures in the margin indicate full marks.
Group A
Attempt any TWO questions.(2 × 10 = 20)
- 1.10
Explain the different components of data warehouse. How data cube precomputation is performed? Describe.
- 2.10
Write the limitation of Apriori algorithm. Given the objects P1(2,3), P2(4,5), P3(10,40), P4(60,55), P5(70,80), apply K-means algorithm (K = 2) to show the final clusters after 2 iterations. Assume P1 and P3 as initial cluster centroids.
- 3.10
Consider the following training data set.
[figure in the original paper]
Group B
Attempt any EIGHT questions.(8 × 5 = 40)
- 4.5
List any two challenge of multimedia mining. Differentiate between web usage mining and web content mining.
- 5.5
How trust and distrust propagate in social network Explain.
- 6.5
Why data preprocessing is mandatory? Justify.
- 7.5
Describe any five types of OLAP operations.
Answer comingAlso asked in 2080
- 8.5
Given the following data set, find the frequent itemset using Apriori algorithm with minimum
support 3. (5)
T1 {A, B, C, D, E, F}
T2 {B, C, D, E, F, G}
T3 {A, D, E, H}
T4 {A, D, F, I, J}
T5 {B, D, E, K}
- 9.5
Illustrate the hierarchical clustering with an example.
- 10.5
Discuss about overfitting and underfitting. How precision and recall is used to evaluate classifier.
- 11.5
What is the concept mini batch k-means? How DBSCAN works?
Answer comingAlso asked in 2079
- 12.5
How beam search and logic programming is used to mine graph? Explain.
— The End —