# 2024 Travelers NESS Statathon — Data

来源：https://www.kaggle.com/competitions/2024-travelers-ness-statathon/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

## Data Description

The data provided to you and your team consists of variables describing customers that asked for quotes. There are three datasets: at the policy, driver, and vehicle levels. Each row of the policy dataset corresponds to a single policy, which may be associated with multiple drivers and vehicles. Likewise, each row of the driver dataset represents a single driver, and each row of the vehicle dataset represents a single vehicle. It's easy to check that each driver and each vehicle are associated with just one policy. You may assume that all members on a policy live at the same address.

Your company was only able to convert a fraction of the policies found in this sample. The policy dataset also has a training and test split variable called split. Note that the conversion indicator (the response variable) is missing for policies in the test split. Your task is to build a model on the training data and apply your model to predict the conversion indicator for each policy in test data. 

### Policies.csv
policy_id:		                                                     Unique customer identifier <br>
Quote_dt:		                                                     Date the quote was submitted <br>
quoted_amt:		                                                     Quote amount (US dollars) <br>
Prior_carrier_grp:                                                        Prior carrier group <br>
Cov_package_type: 	                                             Level of coverage needed <br>
discount:		                                                     Whether or not a discount was applied to the quote amount <br>
number_drivers:		                                             Number of drivers <br>
credit_score:		                                                    Credit score of primary policy holder <br>
num_loaned_veh:	                                                    Number of vehicles on policy that have a loan associated with them <br>
num_owned_veh:	                                                    Number of owned vehicles on the policy <br>
num_leased_veh:	                                                    Number of leased vehicles on the policy <br>
total_number_veh:	                                                    Total number vehicles on the policy <br>
primary_parking:	                                                    Where car(s) are primarily parked <br>
CAT_zone:		                                                    Catastrophe risk zone <br>
Home_policy_ind:	                                                    Does customer has existing home insurance policy with Peace of Mind <br>
zip:			                                                            US zip code of policy holder <br>
state_id:		                                                            State of policy holder <br>
county_name:		                                            County of policy holder <br>
Agent_cd:		                                                    Unique agent code (8 digits) <br>
split:			                                                    Train/Test split <br>
**convert_ind: 		                                            Conversion indicator (0=no, 1=yes). This is the response variable** <br>

### Drivers.csv:
policy_id:		                                                    Unique customer identifier <br>
gender:			                                                    Gender of driver <br>
age:			                                                            Age of driver <br>
high_education_ind: 	                                            Higher education indicator <br>
safty_rating: 		                                                    Safety rating index of driver <br>
living_status: 		                                                    Driver’s living status (levels = ‘own’, ‘rent’, ‘neither’) <br>

### Vehicles.csv:
policy_id:		                                                    Unique customer identifier <br>
car_no:			                                                    Unique car identifier (per policy) <br>
ownership_type:		                                            Whether the car is loaned, owned or leased <br>
color:			                                                    Vehicle color <br>
age:			                                                            Vehicle age <br>
make_model:		                                                    Make and model of the vehicle

# NOTE
**Training and Test sets are combined across the files, and need to be separated manually by your group!**