Data Mining & Business Intelligence - May 2012

Information Technology (Semester 6)

TOTAL MARKS: 80
TOTAL TIME: 3 HOURS (1) Question 1 is compulsory.
(2) Attempt any three from the remaining questions.
(3) Assume data if required.
(4) Figures to the right indicate full marks.

Solve any four from the following:-

1(a) Compare Data mining and Text mining.(5 marks) 1(b) What is Web Usage Mining?(5 marks) 1(c) What are the major issues in Data Mining?(5 marks) 1(d) Explain multilevel association rules.(5 marks) 1(e) Compare database and data warehouse.(5 marks) 2(a) Explain mining sequence patterns in transactional Databases.(10 marks) 2(b) Explain any one method of hierarchical clustering with example.(10 marks) 3(a) Explain different data stream methodologies.(10 marks) 3(b) Explain Data Integration and Transformation with an example.(10 marks) 4(a) Explain Hoeffding Tree algorithm with example.(10 marks) 4(b) List the dimensions and facts for clinical information system and design star and snowflake schema.(10 marks) 5(a) Explain different OLAP operations and applications.(10 marks) 5(b) Use K-means algorithm to create 3 clusters for given set of values {2,3,6,8,9,15,18,22}(10 marks) 6(a) Design a BI application which will provide Retail Chain Company with features and performance that meet their objectives. Use any Data mining technique.(10 marks) 6(b) Explain Web content mining with reference to crawlers, harvest system, virtual web view and personalization.(10 marks)

Write short notes on any three :-

7(a) Difference between Periodic crawler and Incremental crawler.(7 marks) 7(b) Spatial Data Mining.(7 marks) 7(c) Market Segmentation.(7 marks) 7(d) Outlier analysis.(7 marks)