数据挖掘中的聚类技术在学生成绩分析中的应用

本文针对在大类招生背景下北京科技大学经济管理学院2005级学生的考试成绩,应用数据挖掘技术分析分专业前学生成绩与专业及分专业后课程学习之间可能存在的潜在的联系.首先进行数据预处理以保证数据挖掘结果的质量和提高数据挖掘的效率;然后根据分专业前的课程成绩对学生进行聚类,并分析各类的成绩特征;最后以信息管理与信息系统专业为例,分析各类学生在分专业后的优势课程和较弱课程.     

探究大学生考研择校的贝叶斯判别分析模型

以某高校数学专业考研学生的学习及考研情况为研究对象，首先运用系统聚类分析法对国内数学专业100所高校进行聚类，然后运用多元回归方法建立考研成绩与影响因素间的函数关系，对学生考研成绩进行区间估计；最后建立了目标院校、考研成绩二者与考取院校间的贝叶斯判别分析模型，为学生选择考研目标院校提供了较为科学的决策参考。     

大学生专业选择的调查分析及其启示——以福建省部分高校为例

专业性是高等教育的基本属性,专业选择是大学教育的重要问题,影响高校人才培养质量、高校教育产出绩效和社会人力资源收益。本文以福建省部分高校调查为基础,通过分析大学生专业选择考虑因素、大学生专业认同度、转专业意愿等调查数据,探讨大学生选择专业的现实问题,并提出加强学生专业选择指导和专业兴趣培养、提升高校专业设置与社会需求的契合度、对专业设置适时动态调整、扩大学生专业选择自由度、科学制定转专业政策等建议。     

大类培养模式下检测技术课程的优化整合

为提高大类招生培养模式的教学质量,分析了大类培养对专业课程教学的影响,根据检测技术课程内容教学特点,探讨了教学目标定位和内容优化整合原则,提出了课程内容优化及相应教改方案.     

数据仓库在高校会计分析中的应用

本文介绍了数据仓库在高校财务管理中的用途和建立的必要性,详细叙述了高校数据仓库的内容和建立方法,并通过一个事例重点分析了数据仓库在高校会计分析中的应用。     

高校实施按大类招生培养中存在的问题及对策

当今世界的社会经济、文化、科技迅猛发展,国际间的竞争日趋激烈,科学综合化、技术现代化、经济国际化、社会信息化是当今世界发展的主要趋势.为顺应时代的发展,我国的高等教育正以前所未有的态势,不断进行教育教学改革,以培养国际化的复合型、创新型人才.按大类招生分阶段培养就是我国高等教育在人才培养模式方面的重大改革.它通过近几年全国一些高校的实践,证明它有利于"厚基础、宽口径"的人才培养,降低了考生填报高校专业志愿的风险,使学生能近距离感受市场,零距离触摸专业.取得了很好的效果,得到了高教界和社会的肯定.     

基于财务数据分析的数据仓库模型

财务报表数据是分析判断企业经营状况的重要指标,是企业做出及时、准确的决策的重要依据。本文通过介绍数据仓库结构及其相关技术,结合财务分析的特点,提出了基于智能财务分析的数据仓库模型设计方案。     

大类培养模式下检测技术课程的优化整合

为提高大类招生培养模式的教学质量,分析了大类培养对专业课程教学的影响,根据检测技术课程内容教学特点,探讨了教学目标定位和内容优化整合原则,提出了课程内容优化及相应教改方案。     

教育

高考改革试破＂唯分数论＂ 北京有关学者认为,《国务院关于深化考试招生制度改革的实施意见》,将对中小学基础教育和大学招生产生重大影响。试点主要探索的内容是＂两依据、一参考＂,即探索依据统一高考成绩、依据高中学业水平考试成绩,参考学生综合素质评价的多元录取机制。探索的目的是破解＂唯分数论＂＂一考定终身＂等问题,发挥高考＂指挥棒＂的正确导向作用,增加学生的选择机会,分散学生的应试压力，全面推进素质教育，促进高校科学选才。     

大类培养模式下检测技术课程的优化整合

为提高大类招生培养模式的教学质量，分析了大类培养对专业课程教学的影响，根据检测技术课程内容教学特点，探讨了教学目标定位和内容优化整合原则，提出了课程内容优化及相应教改方案。     

Interactive Effects of Major Response Facilitators

Practitioners and researchers have long been interested in achieving the highest response rate within resource constraints on their mailed surveys. Achieving this high response rate typically has required the selection of the right mix of response-facilitating techniques. The selection decisions were generally made under the assumption that the response-facilitating techniques act independently of one another. The authors have examined the validity of this independence assumption by identifying the major response facilitators in use and then analyzing the results of 531 independent mail survey studies. The authors conclude that major facilitators do not function independently. In fact, it was found that significant joint action interactive effects on response rates do exist. Practitioners and researchers who are faced with the survey design decisions of choosing response facilitators can receive assistance by reviewing the results of this diverse collection of reported experiences.     

OPTIMAL PORTFOLIO SELECTION WITH UPPER BOUNDS FOR INDIVIDUAL SECURITIES*

In this paper, we consider optimal portfolio selection with no short sales and with upper bounds for individual securities. The solution is reached by directy revising the optimal portfolio without upper bounds. Specifically, our analysis is based on the single-index model, as well as the general multi-index model that provides the return generating process for securities in the arbitrage pricing theory. As demonstrated in a simulation study, the proposed algorithm for optimal portfolio selection usually requires very few iterations. Also, since our approach is developed using intuitive reasoning and simple linear algebra, we are able to provide direct and intuitive justifications for the resulting portfolio choice. Therefore this paper should be of interest to both finance academics and practitioners in portfolio management.     

大股东存在下的独立董事对公司业绩的影响——基于内生视角的审视

我国独立董事对公司业绩的治理效果一直是学者们感兴趣的话题,但此前的研究一直忽视了独立董事的内生性问题.本文使用四种模型检验了当大股东存在时独立董事对公司业绩的影响.研究发现,在排除内生性之后,独立董事对业绩的影响并不显著.本文认为,造成这种现象的原因在于当公司存在大股东的时候,公司董事会的构成会受到大股东的控制,从而使得独立董事制度流于形式.     

基于DEA的战略组识别

战略组分析是产业组织理论与战略管理理论中的重要分析工具。但战略组的概念模糊性和战略维度和变量选择以及聚类方法的主观性,使得关于战略组识别存在着矛盾的结论。DEA是适合于明确战略组概念和识别战略组的方法。修正后的DEA,如DEA-Window,特别是最优权多重性问题的解决,能较好地识别战略组。     

Early Labour Market Returns to College Subject

Abstract. We estimate early labour market outcomes of Italian university graduates across college subjects. We devote great attention to endogenous selection issues using alternative methods to control for potential self‐selection associated with the choice of the degree subject in order to unravel the causal link between college major and subsequent outcomes in the labour market. Our results suggest that ‘quantitative’ fields (i.e. Sciences, Engineering, and Economics) increase not only the speed of transition into the first job and employment probability but also early earnings, conditional on employment.     

基于元网络分析的重大基础设施建设项目风险评估框架与实证

重大基础设施项目具有战略性、集成性、复杂性等特征，项目容易受到多种风险因素的综合影响，导致项目目标的偏离。现有风险评估与风险决策的方法缺乏对于风险因素、风险事件之间关联的分析。为了实现重大基础设施建设项目综合系统的风险评估，本文采用元网络分析方法，构建项目目标、风险事件和风险因素的交互模型，揭示重大基础设施风险事件发生机制的黑箱过程。风险评估过程中，通过多个网络叠加运算分析每个风险因素对于各种风险事件以及项目各目标的影响情况，改进了以往仅对风险因素单一影响程度的风险评估方法。同时，本研究选择我国某河流水电站过坝运输项目方案比选的风险评估过程验证方法的适用性。     

A Sequential Selection Problem*

In this study we formulate a sequential selection problem. In a setting where a choice sequence among candidates is established for filling a job position, the analysis explicitly takes into account the benefits from the hiring, the risk of rejection of the job offer, and the costs due to delays in filling the position. The proposed solution, which is both intuitive and simple, is able to capture analytically the decision process. We also illustrate the versatility of the analysis by considering several other relevant sequential selection settings.     

INFLUENCE OF MISSING ATTRIBUTES ON SELECTING A BEST MULTIATTRIBUTED ALTERNATIVE

Alternatives involving many factors arc difficult to evaluate because of multiple underlying competing objectives. If evaluation is based on an incomplete set of factors, and if the purpose of the evaluation is to select a single overall best alternative, inferior alternatives may be selected with surprising frequency and/or severe negative impact. At the same time, sensitivity analysis of evaluation scores based on statistical criteria can easily mask the impact and the frequency of selection of inferior alternatives. In this paper, criteria appropriate to reflect the decision impact are developed and both the frequency and impact of the selection of inferior alternatives are demonstrated empirically. Previous studies based on statistical criteria [1] [9] indicated minimal impact on overall evaluation and selection. This paper demonstrates that high statistical criterion values coexist with frequent and/or serious errors of selection.     

Classifying capital projects for top management decision-making

This paper is an attempt to redress a perceived imbalance in the research and literature of capital project analysis. There is a plethora of work on the quantitative aspects of project analysis, yet empirical surveys show limited use of such techniques. There is limited work on the organizational processes of project selection, but there appears to be little or no work taking place on formal organizational systems for project selection.The more quantitative literature generally takes a deductive approach using a model developed from microeconomics based on the assumption that the objective of the firm is the maximization of owners' wealth. In this paper it is argued that there is a need to take an inductive approach and place the capital investment decision in its organizational setting. This paper looks at the formal capital budgeting system within the corporate setting.It is suggested that the specific capital investment decision takes place against the background of a set of policies and constraints, which are more or less explicit.The selection of corporate projects is a complex issue, but to provide some structure so that the problems can be processed by the organization, a capital budgeting system is designed. Part of this system is the classification of projects according to some criteria. It would therefore appear that the purpose of this classification system is to aid capital project selection within an organizational context.A consideration of classification systems for capital projects is undertaken, this is followed by a survey of the classification systems which have been proposed in the capital investment literature. Finally a classification system based upon specific criteria is proposed.     

基于动态分类器集成选择的不完整数据客户分类方法实证研究

在管理决策的制定中,分类已经成为一种十分重要的方法和技术。由于现实客户数据常常是不完整的,因此,研究不完整数据的客户分类问题具有重要意义。通过分析以往分类过程中对不完整数据的处理方法,提出了一种基于动态分类器集成选择的不完整数据分类方法DCES-ID。分别在UCI客户分类数据集以及某券商客户数据集上进行分类的实验和实证分析。结果表明,与已有的6种分类算法相比,DCES-ID算法具有更高的分类准确性及稳定性,能够更有效地进行客户分类。