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

Table 3

. Parameters list of GBDT model.

No.	Parameters name	Implication
1	n_estimators	Maximum number of iterations for weak learners
2	Loss	Loss function. Two choices: “deviance” and “exponential.” Default: “deviance”
3	learning_rate	Each weak learner has a weight factor . Given a smaller learning_rate, such as 0.1, which takes values in the range 0 < learning ≤ 1
4	Subsample	The sampling proportion, which takes the value of (0, 1]. The default value is 1.0, no subsampling is done