A Hybrid Approach of Stepwise Regression, Logistic Regression, Support Vector Machine, and Decision Tree for Forecasting Fraudulent Financial Statements

Table 3

C5.0 cross-validation results.

C5.0 model			Predict value		Hit ratio	Type I error	Type II error
			Non-FFS	FFS
Actual value	CV1	Non-FFS	25	3	83.93%	10.71%	21.42%
		FFS	6	22
	CV2	Non-FFS	25	3	87.50%	10.71%	14.28%
		FFS	4	24
	CV3	Non-FFS	25	3	85.71%	10.71%	17.85%
		FFS	5	23
		Average	25	3	85.71%	10.71%	17.85%
			5	23