EricSiq/indian-insurance-claims-synthetic

这是一个关于医疗保险索赔的数据集，包含索赔ID、受益人信息、保单信息、医院信息、医生信息、住院和出院日期、住院时长、手术信息、诊断代码、费用信息、欺诈信息以及索赔状态等多个特征。数据集分为训练集和测试集，分别包含4000和1000个样本。

This is a dataset about medical insurance claims, including features such as claim ID, beneficiary information, policy information, hospital information, doctor information, admission and discharge dates, length of stay, procedure information, diagnosis codes, billing information, fraud information, and claim status. The dataset is divided into training and test sets, containing 4000 and 1000 samples respectively.