Quantitative Detection of Financial Fraud Based on Deep Learning with Combination of E-Commerce Big Data

Table 1

Confusion matrix applied to the detection model.

		Experiment classification label
		0	1
Predict fraud category	Y	TP: Correct and affirmative.	FP: The error is positive.
		A sample of normal behaviour predicted to be normal behaviour.	A sample of normal behaviour predicted to be fraudulent.
	N	FN: False negative.	TN: Correctly denied.
		A sample of fraudulent behaviour predicted as normal behaviour.	A sample of fraudulent behaviour predicted to be fraudulent.