Engineering BE Computer Engineering Sem 8 December 2018 2018 Data Warehouse And Mining Question Paper - Mumbai University | munotes

Questions asked in this paper

1. Q2 Answer any three out of remaining questions
2. Q1 a) Information requirements are recorded for “Hotel occupancy” considering dimensions like Hotel, Room and Time. Few Facts recorded are vacant rooms, occupied rooms, number of occupants, etc Answer the following questions for this problem: 10 marks
   • i. Design the star schema
   • ii. Can you convert this star schema to a snowflake If yes, justify and draw the snowflake schema
   • b) Explain Data mining as a step in KDD the architecture of typical data 10
3. Q2 a) wants to record the Marks for the courses completed by students using the dimensions: I) Course, IT) Student, HT) Time & a measure Aggregate marks Create a Cube and perform following OLAP. operations : 10 marks
   • b) Apply the Naive Bayes classifier algorithm to classify an unknown sample The sample data set is as follows: 10
   • a) Discuss Data Warehouse design strategies in detail? 10
   • b) Discuss the types of attributes and data visualization for data exploration. Paper Subject Code: 52706 Data Warehouse and Mining 10
4. Q4 a) Discuss various OLAP models and their architecture. 10 marks
   • b) Find clusters using k-means clustering algorithm, if we have several objects (4 types of medicines) and each object have two attributes or features as shown in table below. The intention is to group these objects into k = 2 group of medicine based on the two features (pH and weight index) 10
5. Q5 a) Discuss the process of extraction, transformation and loading with a neat and labelled diagram 10 marks
   • b) A database has five transactions. Let minimum support = 40% and minimum 10
6. Q1 Find all frequent patterns using Apriori Algorithm Write short note on the following (Answer any FOUR) [20]
   • i) Applications of Data Mining (minimum two in detail)
   • iv) Updates to dimension tables
   • v) Meta data with example

Read from the scan above, so a character or two may differ. The scan is the original.