基于熵的决策树理论及其在中医证型研究中的应用

本文使用基于熵的决策树理论对中医证型数据进行了研究,指出此方法对自变量和应变量都是定性指标的资料,能够得到自变量对鉴别诊断的重要性,且建立的决策树的判别效果较理想。     

基于梯度提升决策树的航班延误分类预测

考虑航空交通网络状态特征对航班延误的影响,将上游的航班延误状态特征加入到预测因素中,并使用梯度提升决策树(Gradient Boost Decision Tree,GBDT)的方法构建了航班延误预测模型.与以往的决策树算法、SVM分类算法、RF算法相比,GBDT算法在航班延误分类预测上具有更高的准确度,可有效提高机场运行管理效率.     

决策树分类模型在工程项目评标风险预警中的应用

本文将数据挖掘中的决策树分类方法运用到工程项目评标数据分析,从200多个天津市工程项目招投标打分数据中,随机抽取15个招投标项目中的67个承包商的评标专家打分数据进行分析,得到中标承包商技术和商务评分分界点,进而得到工程项目潜在风险的预警阈值,然后借助因子分析辨识出风险来源并进行预警。     

基于CHAID决策树的个人收入分析

本文提出了应用CHAID决策树方法来分析国民个人收入。首先本文全面分析了CHAID决策树的构造过程,最后通过实证分析,从大量的个人信息数据集中,运用CHAID决策树构建出了一个分析模型,该模型提供了许多潜在的、有用的信息。     

基于决策树算法的上市公司股东行为研究

本文从生态学视角出发,将研究焦点深入到上市公司内部的股东层面。通过将上市公司股东进行生态学的种群划分,刻画不同类型股东所处的生态位,研究分析不同生态位的股东群体之间的关系和行为表现。基于国泰安数据库和CCER数据库2643家上市公司股东2008-2014年四个季度约60万条记录数据,将决策树算法用于股东统计分类和行为分析上,尝试了一种具有速度快、精确度高的特点的统计分析方法;通过分析发现股东持股排名的生态位维度对股东增减持行为和程度影响最大,为进一步的治理决策提供了依据。     

基于相似度的样本分类算法

结合粗糙集理论中相似关系的思想,提出了一种基本相似度的样本分类算法.并通过实例说明了该分类算法的有效性。     

基于变精度加权平均粗糙度决策树的财务预警研究

运用聚类方法把公司财务状况分为5个等级,分别为财务状况健康,良好,一般,预警和危机,与以往将研究样本分为ST和非ST两类的财务预警模型相比,5分类模型更加精确合理,贴近实际。同时基于指标相关性和指标重要度对33个财务指标进行了约简,得到9个能够反映企业财务状况的财务指标。以约简后的9个指标及5个等级的财务状况来建立决策树,指标体系和财务等级更加合理。树的生成过程运用粗糙集中的变精度加权平均粗糙度作为选择测试属性的方法,每次选择变精度加权平均粗糙度值最小的属性作为分支结点。变精度加权平均粗糙度的应用提高了决策树的防噪声能力,复杂性较低且能有效提高分类效果。实证研究表明将它应用到财务预警领域,提高了财务预警的分类精度。     

多状态系统的LAD决策树的建树方法研究

LAD( Logistic Data Analysis Tree)是一种逻辑数据分析技术 ,它将布尔代数和优化分析方法引入到了判别分析领域 ,提出了一种布尔变量集合的变量筛选和建模方法 ,并可以对冗余模式进行可视化识别与删除 .但目前的 LAD技术还仅限于二状态 ,而且算法复杂 .本文将 LAD决策树推广到了多状态情形 ,以三状态下建立 LAD决策树为例 ,提出了不可分辨度的定义 ,并以其下降最大作为寻找最优决策树的依据 .说明多状态下建立 LAD决策树的计算方法及重要的算法步骤 .最后 ,本文以鄱阳湖地区洪涝灾害影响研究为案例 ,采用 LAD决策树方法对其进行判别分析 .     

基于迭代自适应随机决策树的个人信用评估模型研究

信用评估是商业银行控制和防范信贷风险的关键途径.决策树模型较好的直观解释性使其成为当前个人信用评估中的常用模型,但决策树模型存在容易导致过拟合且预测精度有限的问题.通过在决策树模型算法中引入类随机森林随机有放回的抽样模式,运用机器自动循环迭代寻求最优树的建模思想,建立了自适应最优C5.0决策树个人信用评估模型.该模型具有快速收敛特征变量、较好的泛化能力和高预测精度的特点,在实证分析中对商业银行个人信用评估模型质量提升带来比较明显的改进效果.     

区间数相似度研究

对区间数相似性问题进行了探讨.定义了区间数相似度的概念,给出了度量区间数相似度的一个简洁公式,详细研究了它的一些优良性质,如:自反性、对称性和传递性等,并且研究了区间数相似度公式与区间数排序的可能度公式之间的关系,从而为区间数的实际应用奠定了理论基础.     

布尔函数的判定树复杂性及问题

设f（x₁,x₂,…,x_n）是一个布尔函数。如果计算f（x₁,x₂,…,x_n）的每个判定树算法在最坏情况下都要检查所有n个变量才能求得f的值,则称f是诡秘函数。1988年,A.C.C.Yao提出一个问题:如果一个单调非平凡的布尔函数f（x₁,x₂,…,x_n）在循环群C_m×C_n的直积的可迁作用下不变,则f是诡秘的吗?对这个问题的肯定回答支持著名的Rivest-Vuillemin猜想.本文将部分地解答这一问题.     

Decision trees for monotone price models

In economic decision problems such as credit loan approval or risk analysis, models are required to be monotone with respect to the decision variables involved. Also in hedonic price models it is natural to impose monotonicity constraints on the price rule or function. If a model is obtained by a unbiased search through the data, it mostly does not have this property even if the underlying database is monotone. In this paper, we present methods to enforce monotonicity of decision trees for price prediction. Measures for the degree of monotonicity of data are defined and an algorithm is constructed to make non-monotone data sets monotone. It is shown that monotone data truncated with noise can be restored almost to the original data by applying this algorithm. Furthermore, we demonstrate in a case study on house prices that monotone decision trees derived from cleaned data have significantly smaller prediction errors than trees generated using raw data.MSC code: 90-08 (Computational methods)     

Classification Trees With Bivariate Linear Discriminant Node Models

This article introduces a classification tree algorithm that can simultaneously reduce tree size, improve class prediction, and enhance data visualization. We accomplish this by fitting a bivariate linear discriminant model to the data in each node. Standard algorithms can produce fairly large tree structures because they employ a very simple node model, wherein the entire partition associated with a node is assigned to one class. We reduce the size of our trees by letting the discriminant models share part of the data complexity. Being themselves classifiers, the discriminant models can also help to improve prediction accuracy. Finally, because the discriminant models use only two predictor variables at a time, their effects are easily visualized by means of two-dimensional plots. Our algorithm does not simply fit discriminant models to the terminal nodes of a pruned tree, as this does not reduce the size of the tree. Instead, discriminant modeling is carried out in all phases of tree growth and the misclassification costs of the node models are explicitly used to prune the tree. Our algorithm is also distinct from the “linear combination split” algorithms that partition the data space with arbitrarily oriented hyperplanes. We use axis-orthogonal splits to preserve the interpretability of the tree structures. An extensive empirical study with real datasets shows that, in general, our algorithm has better prediction power than many other tree or nontree algorithms.     

Decision support for spare parts acquisition in post product life cycle

A major task in service management is the timely and cost efficient provision of spare parts for durable products. This especially holds good, when the regular production of the product, its components and parts has been discontinued, but customer service still has to be guaranteed for quite a long time. In such post product life cycle period, three options are available to organize the spare parts acquisition, namely (i) setting up a single large order within the final lot of regular production, (ii) performing extra production runs until the end of service and (iii) using remanufacturing to gain spare parts from used products. These three options are characterized by different cost and flexibility properties. Due to the time-variability and uncertainty of demands for spare parts and also that of the returns of used products, it is a challenging task to find out the optimal combination of these three options. In this paper we show how this problem can be modeled and solved by Decision Tree and stochastic Dynamic Programming procedure. Based on the Dynamic Programming approach a heuristic method is proposed, which can be employed to come up with a simple solution procedure for real-world spare parts acquisition problems during the post product life cycle. A numerical example is presented to demonstrate the application of the solution methods described in the paper.     

Regression Tree Analysis Using TARGET

Regression trees are a popular alternative to classical regression methods. A number of approaches exist for constructing regression trees. Most of these techniques, including CART, are sequential in nature and locally optimal at each node split, so the final tree solution found may not be the best tree overall. In addition, small changes in the training data often lead to large changes in the final result due to the relative instability of these greedy tree-growing algorithms. Ensemble techniques, such as random forests, attempt to take advantage of this instability by growing a forest of trees from the data and averaging their predictions. The predictive performance is improved, but the simplicity of a single-tree solution is lost.

In earlier work, we introduced the Tree Analysis with Randomly Generated and Evolved Trees (TARGET) method for constructing classification trees via genetic algorithms. In this article, we extend the TARGET approach to regression trees. Simulated data and real world data are used to illustrate the TARGET process and compare its performance to CART, Bayesian CART, and random forests. The empirical results indicate that TARGET regression trees have better predictive performance than recursive partitioning methods, such as CART, and single-tree stochastic search methods, such as Bayesian CART. The predictive performance of TARGET is slightly worse than that of ensemble methods, such as random forests, but the TARGET solutions are far more interpretable.     

Benchmark optimization and attribute identification for improvement of container terminals

The aim of this paper is to optimize the benchmarks and prioritize the variables of decision-making units (DMUs) in data envelopment analysis (DEA) model. In DEA, there is no scope to differentiate and identify threats for efficient DMUs from the inefficient set. Although benchmarks in DEA allow for identification of targets for improvement, it does not prioritize targets or prescribe level-wise improvement path for inefficient units. This paper presents a decision tree based DEA model to enhance the capability and flexibility of classical DEA. The approach is illustrated through its application to container port industry. The method proceeds by construction of multiple efficient frontiers to identify threats for efficient/inefficient DMUs, provide level-wise reference set for inefficient terminals and diagnose the factors that differentiate the performance of inefficient DMUs. It is followed by identification of significant attributes crucial for improvement in different performance levels. The application of this approach will enable decision makers to identify threats and opportunities facing their business and to improve inefficient units relative to their maximum capacity. In addition, it will help them to make intelligent investment on target factors that can improve their firms’ productivity.     

物元评判模型及其在学习评价中的应用

对物元评判模型进行了分析，将它应用于学生学习评价，定义了新的关联度函数，分析表明模型是一类优良模型，能有效的运用于学生学习评价中。