Data Mining & Business Intelligence - Dec 2014
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. 1(a) What is Web Structure mining? What are the techniques used for it?(5 marks) 1(b) Compare OLTP and OLAP(5 marks) 1(c) Consider the transaction database.
|1||A, B, D|
|2||B, C, D|
|5||A, B, C, D|
Use apriori algorithm with minimum support of 30%. Find all frequency Item-sets.(5 marks) 1(d) What is multidimensional association rule?(5 marks) 2 A manufacturing company has a huge sales network. To control the sales, it is divided in the regions. Each region has multiple zones. Each zone has different cities. Each sales person is allocated different cities. The object is to track sales figure at different granularity levels of region. Also to count number of products sold. Products are categorized as high end and low end products. Develop BI application, taking into consideration of above granularity levels of region, sales person, Product and the Quarterly, yearly and monthly sales. Also it should predict Zone wise, product-wise sales for subsequent quarters
- Identify facts and dimensions and hence draw information package diagram.
- Design suitable DWH schema.
- Identify suitable DM algorithm for predicting the sales.
- Give justification for all the decisions you have taken for the design.
Answer any two questions.
7(a) What is text mining? Explain different approaches of text mining.(10 marks) 7(b) What is CLICK- STREAM mining?(10 marks) 7(c) What are the applications of Web usage mining? What is Web log? Give typical structure of web log?(10 marks)