Chinese Listed Companies Financial Statement Dataset

The Chinese Listed Companies Financial Statement Dataset (China-FSD) comprises 33,664 annual financial reports from 5,254 Chinese listed companies, spanning the years 2014 to 2022. The data is sourced from the China Securities Regulatory Commission (CSRC). Each financial statement is treated as a node characterized by 247 features. The dataset is severely imbalanced, as fraudulent nodes constitute merely 4.6\\% of all nodes, whereas the remainder are benign.