Preprocessing Application for Car Insurance Claim Classification Model

The use of data in various industry sectors becomes a necessity in predicting or deciding on one of them is the use of car insurance data related to claims made by vehicle owners. The data can later be used by insurance companies to be analyzed related to car insurance claims both from the owner's side of the car and from the condition of the car. This paper will discuss the preprocessing data on auto insurance claim data in America with the aim of later making a data model so that it can be used next to see the accuracy of the data processed classification. The results of processing data and data classification can help car insurance companies in deciding a policy or problem that occurs accurately and measurable. The data used in this paper is data that still has a missing value. Therefore, data cleaning is done by cleaning, filtering, and combining these data. The study used the Car Insurance Claim Data dataset downloaded on kaggle's website. The results showed that the JRIP algorithm had the best accuracy of 83.09 percent (before the preprocessing dataset) and 83.14 percent (after the preprocessing dataset was applied) in the 10 fold cross-validation test mode. With an increased level of accuracy, the data can be better used again as an example for forecasting tau as a reference company to trigger something related to the data.