The principle of operation of XGBoost can be Phone Number List divided into the following parts: 1) The objective function of XGBoost: To prevent overfitting, a regularization term is added the objective function of XGBoost, and the loss function is chosen to Phone Number List be able to perform a second-order Taylor expansion (Chen and Xgboost 2016). The objective function is shown in Eq. (2). minωt∑t=1T(Gtωt+12(Ht+λ)ω2t)+γT (2) 2) Determine Phone Number List the output of the leaf nodes of the base .
CART tree: The loss function should satisfy both Phone Number List the second-order derivative and Ht + λ > 0, then the absolute value of the objective Phone Number List function is obtained by Eq. (3). y=∑t=1T(−G2t2(Ht+λ))+γT (3) where T is the total number of leaf nodes of the base CART regression tree; ω is the output fraction of the leaf nodes of the Phone Number List tree; t = 1, 2, …; T is the output value of the t-th leaf node of the base CART regression tree; and γ and λ is the coefficients of the regularization terms, respectively; y is the absolute value of the Phone Number List objective function. 3) Determine the structure of the base .
CART tree: whether the leaf node is suitable to Phone Number List be extended is determined by a recursive algorithm. For the particular leaf node Phone Number List which needs to be extended, its objective function value is first calculated before Phone Number List the extension. The extended objective function value is calculated after extending. According Phone Number List to each taken value, two new leaf nodes are segmented. Then the difference between the node’s values of two new leaves is calculated, and the feature achieved the maximum value is Phone Number List used, and its value is used to segment the leaf nodes. 4)