Dataset Hub

This synthetic dataset was generated with 3D rendering tools for early detection of Pine Wilt Disease (PWD). By combining real and synthetic data, the dataset raises the PWD F1 score to 92.88%, aiding forest protection and being applicable to other agricultural domains.

This dataset contains 1,339 health‑insurance records and is intended for predicting individual medical charges. Features include age (numeric), sex (categorical), BMI (numeric), number of children (numeric), smoker status (categorical), region (categorical), and the target variable charges (numeric). The data are synthetic, generated to match the original dataset with a 95% similarity to address privacy concerns.