In this project, you are required to build a model to identify inputs or predictors that differentiate risky from non-risky clients (based on patterns about previous clients) in an insurance company. You are asked to use those inputs to predict new customers who might be charged at a high, medium, or low premium. A sample data file can be found on Blackboard. The data file consists of 490 cases and 14 variables about past and current clients of the insurance company. The data set contains client-related information such as vehicle type, ownership type, years of owning a vehicle, employment, demographic data, and the outcome or dependent variable for each client, classifying each case as low, medium, or high based on the institution's past data. In the data file, 490 data points can be found under the Excel Sheet labeled Insurance Sample File. Using the sample data points in the attached file,

1. Build a decision tree model consisting of three independent variables that will best provide you with insights to learn about the characteristics of the problem. Test its performance on the 15 data points listed under New Data, found at the bottom of the Sheet.
2. Create two additional decision tree models, using three independent variables different from the ones used to create the first decision tree model.
3. Compare the three models and report following the CRISP-DM approach. Your report should include a discussion on the resulting performance of the test set (i.e., New Data) and recommendations to an Insurance Manager who needs to use your model to determine customers who should be charged low medium, or high premiums. Be sure to include any assumptions.

New Data
Pickup	2004	Lease	Personal Injury	Motorcycle	5	33	M	Divorced	69	1	1	Unemployed
Crossover	2010	Owner	Comprehensive Coverage	Business	7	71	F	Divorced	56	3	0	Management
SUV	2019	Lease	Liability Coverage	Boat	20	139	F	Divorced	21	1	1	Management
Sedan	2016	Lease	Medical Coverage	Landlord	2	44	F	Married	55	2	5	Management
Pickup	2012	Owner	Comprehensive Coverage	Flood	13	43	M	Married	43	5	3	Unemployed
Pickup	2020	Lease	Collision Coverage	Motorcycle	2	107	M	Single	72	3	3	Skilled
Sedan	2016	Owner	Uninsured	Boat	6	79	F	Married	20	5	3	Skilled
Wagon	2006	Owner	Collision Coverage	Condo	20	49	F	Single	48	3	0	Skilled
Wagon	2018	Owner	Uninsured	Boat	12	120	F	Married	34	0	3	Management
Wagon	2016	Lease	Liability Coverage	Business	1	85	M	Married	52	4	4	Unemployed
Pickup	2017	Lease	Medical Coverage	Motorcycle	12	117	M	Divorced	40	2	0	Skilled
Minivan	2015	Owner	Collision Coverage	Condo	3	134	F	Divorced	16	4	0	Unemployed
Sedan	2019	Lease	Comprehensive Coverage	Flood	9	131	M	Married	19	1	1	Management
SUV	2015	Lease	Medical Coverage	Landlord	19	60	F	Divorced	54	2	5	Unemployed
Pickup	2011	Owner	Medical Coverage	Flood	19	115	M	Married	17	2	1	Skilled