[Retracted] Application Analysis of the Machine Learning Fusion Model in Building a Financial Fraud Prediction Model

Table 4

. Parameter tuning results of GBDT model.

Parameters name	Tuning range	Tuning results	AUC after tuning
Loss	[“deviance” and “exponential”]	deviance	0.898
n_estimators	[10, 100]	80
Subsample	[0.5, 1]	0.7
learning_rate	[0.01, 1]	0.01