Subject: Data Mining Correct Answer with good Explanation 1. When does it make s
ID: 663735 • Letter: S
Question
Subject: Data Mining
Correct Answer with good Explanation
1. When does it make sense to use closeness as a filter to trim data?
2. Name two situation in which you would want to use clustering based on SNN similarity or density.
3 As the number of clustered dimensions increases there is a potential problem, what is it, and how you can overcome it?
4 What is anomaly detection? (Describe the different techniques)
5. What is the advantage of using binary files over text files? (Describe the disadvantages too)
Explanation / Answer
5.
The implementations on different platforms can introduce various
differences.if you open file in the text mode, you cant read over the EOF
char.This is a problem if the file is a binary file
4.
it is a form of classification
it is used to detecting fraud network intrusion
techniques are
. model based
. proximity based
. density based
2.
Behavior of similarity and distance measures in high dimensions
Dealing with Non-globular Clusters using Representative Points
Noise Removal and Detection of Representative Points