Sustainable efficiency drivers in Eurasian airports: Fuzzy NDEA approach based on Shannon's entropy

This research explores the physical infrastructure and flight consolidation efficiency drivers of Eurasian airports regarding their infrastructure and movement productivity levels. A novel Fuzzy Double-Frontier Network DEA (FDFNDEA) model is proposed to investigate the relationship between desirable (freight and passenger turnovers) and undesirable (pollutant emission levels due to aircraft movements) outputs against the respective infrastructure usage, fuel consumed, and movements performed at each of the 23 Eurasian airports from 2000 to 2018. This balance between desirable and undesirable outputs emerges spatially and temporally due to the evolution of the airport system's productive resources at each one of the Eurasian countries over the period observed. Shannon's entropy is used as the cornerstone to quantify the input and output vagueness of this evolution in Triangular Fuzzy Numbers (TFN), thus allowing the accurate building of alternative optimistic and pessimistic double-frontier efficiency. Differently from previous research, Shannon's entropy is the key for measuring input and output vagueness levels in light of the maximal entropy principle. This principle states that the distribution that best represents the current state of knowledge is the one with largest entropy. Maximal entropy yields bias-free decision-making in the sense that the input/output distributional profiles for Eurasian airports contain the maximal possible heterogeneity, working as a robust or best/worst-case scenario against eventual unconsidered assumptions. Hence, optimistic and pessimistic Malmquist Productivity Indexes (MPI) for overall and each stage productivity results are subsequently regressed against contextual variables related to airport characteristics and regional socio-demographic and economic indicators of each Eurasian country using bootstrapped Cauchy regressions. The findings revealed the spatial heterogeneity of productivity factors and airport performance across Eurasia. Results also demonstrated the negative impact of income inequality and the positive impact of private participation on technological progression in the Eurasian airport industry.     

基于粗糙集理论的决策树方法在贷款客户信用评估中的应用

决策树是数据挖掘中常用的分类技术，其生成的规则便于决策者理解和应用。然而面对较多的属性且含有冗余和噪声属性的记录集生成的决策树时，无法删除冗余属性，造成运算过程复杂。本文旨在通过应用粗糙集理论，将其与决策树方法进行结合，对属性进行约简，降低运算复杂度，并生成相对简化的规则形式，并将其应用到银行个人贷款客户信用评估之中。     

企业信息化过程中知识转移能力研究

考虑到企业信息化建设过程中知识转移的能力具有灰色性和模糊性的特点,传统的分析方法具有很大的局限性。本文采用基于信息熵权值的多层次灰色评价理论,对信息化过程中知识转移的能力的多级指标体系进行综合评判,为企业提供决策以及改进的依据,最后给出运用该方法的一个实例。该方法具有较强的实际应用价值。     

On the Role of Weight Restrictions in Data Envelopment Analysis

This paper examines the role that weight restrictions play in Data Envelopment Analysis (DEA). It is argued that the decision to include a factor (input or output) in a DEA model represents an implicit judgement that the factor has a non-trivial weight. It therefore seems perverse to allow DEA to assign a trivial weight to that factor in assessing the efficiency of a unit. There is therefore a strong case for imposing restrictions on factor weights. However, many existing methods of weight restriction are in practice unwieldy. This paper proposes an alternative approach we term contingent weight restriction which is both practical and intellectually consistent with the DEA philosophy. The paper explores the implications of alternative methods of weight restriction using simulated data from a well known production process.     

浅析人力资本的保值与增值

本文从熵的角度解释了人力资本的贬值问题，认为熵与人力资本有着紧密的联系，并从人力资本的生产过程和使用过程两方面提出了人力资本保值与增值的对策。     

On Choosing and Bounding Probability Metrics

When studying convergence of measures, an important issue is the choice of probability metric. We provide a summary and some new results concerning bounds among some important probability metrics/distances that are used by statisticians and probabilists. Knowledge of other metrics can provide a means of deriving bounds for another one in an applied problem. Considering other metrics can also provide alternate insights. We also give examples that show that rates of convergence can strongly depend on the metric chosen. Careful consideration is necessary when choosing a metric.     

煤炭资源型城市聚集经济与城市化水平研究

运用可变权系数综合评价模型对2002年中国煤炭资源型城市城市化水平进行测度;基于1999～2002年度煤炭城市面板数据,应用随机效应模型估计煤炭城市聚集经济水平;结果表明,我国煤炭城市城市空间经济结构效率和其城市化水平并不具有正相关性,许多城市化水平相对较高的煤炭城市的聚集经济较差,并没有显示出城市化经济的优势.     

基于信息熵的山东省入境旅游消费结构演变分析

旅游者的消费结构对一个地区旅游经济的发展有重要意义。通过信息熵的引用，以山东省历年入境旅游者旅游消费结构统计数据为基础，归纳总结了山东省入境旅游者旅游消费特征和演变规律，并对山东省旅游消费结构的发展趋势进行了预测。     

自适应聚类视角下学科领域主题分析——以物流学科为例

基于改进关键词重要性和近邻传播聚类算法,提出了一种学科领域主题分析方法,通过词频分析法和作者潜意识行为计算高频关键词权重,借助共词分析和Ochiai系数构建带权重高频关键词相似性矩阵,利用近邻传播聚类算法对学科领域主题进行自适应提取与分析。以CSSCI收录的2015—2019年物流学科领域期刊论文为研究对象,借助新方法对其进行主题分析,研究结果表明:高重要性的关键词不一定是核心主题,核心主题与同一簇内其它成员关键词最为相似。与此同时,近五年物流学科存在“降本增效”“区域物流一体化”“现代物流技术研究与创新”“物流体制改革与产业转型升级”“农村物流与农产品物流”“电子商务与跨境电商”“可持续发展理念”等七大热门主题。