Vehicle Claims

The code to create the dataset is available here. The dataset used in the paper is available on github

• Maker - Categorical - The brand of the vehicle.
• GenModel - Categorical - The model of the vehicle.
• Color - Categorical - Colour of the vehicle.
• Reg_Year - Categorical - Year of Registration.
• Body_Type - Categorical - Eg. SUV, Convertible.
• Runned_Miles - Numerical - Distance covered by the vehicle.
• Engin_Size - Categorical - Size of engine.
• GearBox - Categorical - Automatic, Manual.
• FuelType - Categorical - Petrol, Diesel.
• Price - Numerical - Price of vehicle.
• Seat_num - Numerical - Number of seats.
• Door_num - Numerical - Number of Doors.
• issue - Categorical - Type of damage.
• issue_id - Categorical - Specific damage.
• repair_complexity - Categorical - Difficulty to repair the vehicle.
• repair_hours - Numerical - Time required to finish the job.
• repair_cost - Numerical - Cost of repair.

Other attributes are not used for evaluation in this work. breakdown_date and repair_date were added with the idea of inserting anomalies based on the number of days required to repair the vehicle.