1. Objective: We want to predict whether a customer will change providers (denoted as Churn) based on the usage pattern of customers.

2.	License: Free to use, with citation request.

3. Data Source: http://www.sgi.com/tech/mlc/db/churn.all

4. DataSet Info: This is a dataset artificial based on claims similar to real world.

5. Field Meanings:
	A. State: The State where the customer is from.
	B. Account Length: How long the account has been active.
	C. Area Code: Area Code.
	D. Phone: Phone number.
	E. Int'l Plan: Indicate whether the customer has International Plan.
	F. VMail Plan: Indicate whether the customer has Voice Mail Plan.
	G. VMail Message: Number of voice mail messages.
	H. Day Mins: Total day minutes.
	I. Day Calls: Total day calls.
	J. Day Charge: Total day charge.
	K. Eve Mins: Total evening minutes.
	L. Eve Calls: Total evening calls.
	M. Eve Charge: Total evening charge.
	N. Night Mins: Total night minutes.
	O. Night Calls: Total night calls.
	P. Night Charge: Total night charge.
	Q. Intl Mins: Total international minutes.
	R. Intl Calls: Total international calls.
	S. Intl Charge: Total international charge.
	T. CustServ Calls: Numbers of calls to customer service.
	U. Churn?: Whether the customer choose to churn or not.

6. Parameter Selection:
	A. Dashboard Usage: Predict Categorical Fields
	Settings:
	   1) Search command: | inputlookup churn.csv
	   2) Field to predict: Churn?
	   3) Fields to use for predicting: CustServ Calls, Day Mins, Eve Mins, Int'l Plan, Intl Calls, Intl Charge, Intl Mins, Night Charge, Night Mins, VMail Plan