[Retracted] Using an Optimized Learning Vector Quantization- (LVQ-) Based Neural Network in Accounting Fraud Recognition

Table 3

Discrimination results of neural network model training and test samples based on LVQ.

Company type	Training samples (320 pairs in total)			Test samples (150 pairs in total)
	Fraud company	Matching company	Classification accuracy	Fraud company	Matching company	Classification accuracy
Fraud company	305	15	95.45	136	14	88.54
Matching company	18	312	35.98	18	132	91.54
Overall correct rate	93.54			90.48