1. One of your driver variables in a data set is Customers Income. The majority of the records in the customer income variable ranges from a low of $30,000 to a high of $120,000. However, one customers income is $2,350,000. (6pts)

a. What is this data point $2,350,000 referred to? (technical name)

b. Would you include it in your data when you mine your data? (yes/no answer)

2. You want to determine whether the length of time an employee has worked for your company is an important variable that affects/drives their likelihood to quit their job, but all you have is the date when the employee began working for you. What could you do to generate duration of employment (e.g. how long the employee has been working at your company). Answer in one to two sentences.

3) You have mined your data with a neural network and your R^2 came up with (.99). Describe two important potential reasons why your model produced near perfect results? Answer in a few sentences

4) The CEO of a company sees that many financial metrics are deteriorating (e.g. Total Sales, Share Price, etc.) and wants to know WHAT is Happening with the companys operations, to get a better understanding of where the problems are coming from. As an analyst, which type of analytics should you show him/her. Retrospective analytics or Prospective/predictive analytics. Answer in one word

6) The data miner has a large volume of data and is not sure of a target variable and would rather identify related groupings in the data variables rather than relationships between driver and target variables, which method would they use. Place an x before one of the methods below.

__ regression __ Clustering __segmentation __ Neural Nets

7) The data miner wants to identify how price and advertising drive sales for the company and wants to forecast but does not like to use algorithms. Place an x before one of the methods below.

__ regression __ Clustering __segmentation __ Neural Nets