Boost-R: Gradient boosted trees for recurrence data
Boost-R: Gradient boosted trees for recurrence data
复制标题
Boost-R：用于重复数据的梯度提升树
DOI：
10.1080/00224065.2021.1948373
复制
发表时间：
2021
影响因子：
2.5
通讯作者：
Pan, Rong
中科院分区：
文献类型：
--
作者：
Liu, Xiao;Pan, Rong
复发数据来自可靠性、网络安全、医疗保健、在线零售等多学科领域。本文研究了一种基于加法树的方法，称为Boost-R（复发数据增强），用于具有静态和动态特征的复发事件数据。Boost-R构造梯度提升的加性树的集合来估计复发事件过程的累积强度函数，其中通过最小化观测和预测累积强度之间的正则化L2距离来将新树添加到集合。与传统的回归树不同，Boost-R在每个树叶上构造了一个时间依赖函数。来自多个树的这些函数的和产生累积强度的集合估计。基于树的方法的分而治之的性质是有吸引力的，当隐藏的子群体存在于一个异质的人口。回归树的非参数性质有助于避免对事件过程和特征之间的复杂交互进行参数假设。Boost-R的关键见解和优势进行了研究，通过全面的数值例子。Boost-R的数据集和计算机代码可在GitHub上获得。据我们所知，Boost-R是第一个基于梯度提升加法树的方法，用于建模具有静态和动态特征信息的大规模复发事件数据。
Recurrence data arise from multi-disciplinary domains spanning reliability, cyber security, healthcare, online retailing, etc. This paper investigates an additive-tree-based approach, known as Boost-R (Boosting for Recurrence Data), for recurrent event data with both static and dynamic features. Boost-R constructs an ensemble of gradient boosted additive trees to estimate the cumulative intensity function of the recurrent event process, where a new tree is added to the ensemble by minimizing the regularizedL2distance between the observed and predicted cumulative intensity. Unlike conventional regression trees, a time-dependent function is constructed by Boost-R on each tree leaf. The sum of these functions, from multiple trees, yields the ensemble estimator of the cumulative intensity. The divide-and-conquer nature of tree-based methods is appealing when hidden sub-populations exist within a heterogeneous population. The non-parametric nature of regression trees helps to avoid parametric assumptions on the complex interactions between event processes and features. Critical insights and advantages of Boost-R are investigated through comprehensive numerical examples. Datasets and computer code of Boost-R are made available on GitHub. To our best knowledge, Boost-R is the first gradient boosted additive-tree-based approach for modeling large-scale recurrent event data with both static and dynamic feature information.
DOI：
10.1007/978-3-030-10997-4_10
发表时间：
2018-07
期刊：
--
影响因子：
--
作者：
Georg L. Grob;Ângelo Cardoso;C. H. B. Liu;Duncan A. Little;B. Chamberlain
通讯作者：
Georg L. Grob;Ângelo Cardoso;C. H. B. Liu;Duncan A. Little;B. Chamberlain
通过分层非负绞索进行信息传感器和特征选择
影响因子：
2.5
作者：
K. Paynabar;Judy Jin;M. Reed
通讯作者：
M. Reed
FBP：基于边界的树剪枝算法
影响因子：
2.1
作者：
X. Huo;Seoung Bum Kim;K. Tsui;Shuchun Wang
通讯作者：
Shuchun Wang