MODEL PAPER
THIRD SEMESTER, M. Sc INFORMATION TECHNOLOGY

Paper - VII (MIT - 307): Data Mining

1. Question.
1. Briefly describe all phases in the KDD process. How does KDD differ from data mining?
2. Given an initial population {<101010>, <001100>, <010101>, <000010>}, apply the genetic algorithm to find a better population. Suppose the fitness function is defined as the sum of bit values for each individual and that mutation always occurs by negating the second bit. The termination condition is that the average fitness value for the entire population must be greater than 4. Also, an individual is chosen for crossover only if its fitness is greater than 2.
2. Question.
1. Discuss briefly various data mining issues.
2. Apply Bayesian classification on the following set of data: -

   Number	Gender	Height	Class
   1	F	1.6	Short
   2	M	2.0	Tall
   3	F	1.9	Medium
   4	F	1.88	Medium
   5	F	1.7	Short
   6	M	1.85	Medium
   7	F	1.6	Short
   8	M	1.7	Short
   9	M	2.2	Tall
   10	M	2.1	Tall
   11	F	1.8	Medium
   12	M	1.95	Medium
   13	F	1.9	Medium
   14	F	1.8	Medium
   15	F	1.75	Medium

   and classify the tuple < , M, 1.9>
3. Question.
1. Define decision tree and write a decision tree based classification algorithm.
2. How the splitting attribute is selected in decision tree based algorithm. Show it for the training set given in 2(b).
4. Question.
1. Write the K-means clustering algorithm and apply the same for the following data to create three clusters: -
   {2, 4, 10, 12, 3, 20, 30, 11, 25}
2. A major problem with single link algorithm is that clusters consisting of long chains may be created. Describe and illustrate this concept.
5. Question.
1. Define the concept of association rule and describe Apriority algorithm.
2. Apply apriority algorithm for the following transactions to generate association rules taking s = 20% and = 40% -

   Transaction	Items
   t1	Bread, Jam, Butter
   t2	Bread, Butter
   t3	Bread, Milk, Butter
   t4	Curd, Bread
   t5	Curd, Milk
   t6	Bread, Milk

6. Question.
1. Describe Web mining with the help of suitable examples.
2. Given the following sessions: -
   {< A, B, A, C>, < C, B, D, F>, < A, B, A>}, Indicate the sequential patterns, forward sequences and maximal frequent sequences assuming a minimum support of 30%. Assume that each session occurs from a different user.
7. Question.
1. What do you understand from spatial data mining? Describe briefly some of its applications.
2. Describe briefly various data structures used in spatial data mining.
8. Question.
1. What do you understand from temporal data mining? Describe briefly some of its applications.
2. Plot the following time series values as well as the moving average found by replacing a given value with the average of it and ones preceding and following it: -
   {5, 15, 7, 20, 13, 5, 8, 10, 12, 11, 9, 15}.
   For the first and last values, you are to use only the two values available to calculate the average.