Research Article
Monitoring and Analysis of Venture Capital and Corporate Fraud Based on Deep Learning
| Variable name | Symbol | Description |
| Main variable | Corporate fraud | | The dummy variable, is set to 1 if there is corporate fraud, otherwise it is 0 | Fraud frequency | | Count variable, corporate fraud frequency | Venture capital | | The dummy variable, is set to 1 if the VC holds the shares of companies in the current year, otherwise it is 0 |
| Control variable | Audit quality | Audit | The dummy variable, is set to 1 if audit institutions are big 4 accounting firms, otherwise it is 0 | Company size | Size | Natural logarithm of total assets | Performance variable | Roa | Return on assets (ROA) | Board size | Bdsize | The logarithm of the number of directors by the end of the year | CEO duality | Dual | The value is set to 1 if the roles of the CEO and the chair of the board are combined, otherwise it is 0 | Years of being companies | Age | The logarithm of years of being companies | Industry confidence | Tqmed | Median of TobinQ of all companies in the same industry by the end of the year | Industry dummy variable | Industry | Classified according to the industry classification standard of the China securities regulatory commission (CSRC) in 2012 | Year dummy variable | Year | Year dummy variable |
|
|