在数据库中挖掘定量关联规则的方法研究

数据挖掘技术是实现智能决策支持系统的一个重要手段 ,关联规则是数据挖掘的一个重要内容 .传统的 Apriori算法仅适用于挖掘数据间的定性关联关系 ,但数据间的定量关联关系对决策更有帮助 .属性值的离散映射是挖掘定量关联规则的一个重要环节 ,离散映射中属性值区间的划分粒度是影响数据挖掘质量的一个重要因素 .本文结合粗集理论提出了一个确定属性值划分粒度的方法 ,在此基础上设计出一个挖掘定量关联规则的算法 :Apriori 2 ,利用Apriori 2可以挖掘出大量对决策有帮助的定量关联规则     

查询驱动的一种挖掘特征规则的新方法

智能查询是决策支持系统的一个重要内容 ,在数据库中挖掘特征规则是实现智能查询的一个重要手段 .目前的数据挖掘方法都是面向具体问题的 ,不能适应用户灵活的查询需要 .本文结合粗糙集理论 ,提出了一个面向查询的挖掘特征规则的新方法 ,利用该方法挖掘出的特征规则可以在精度上达到最优 .以该算法为核心 ,本文设计出一个查询特征规则的类 SQL命令 ,使用户与系统的交互问答更加方便、灵活     

基于意外度的关联规则深层知识发现及应用研究

为了弥补传统关联规则挖掘产生大量冗余规则、难以直接用于决策支持的不足,本文提出了一种基于用户已有知识的规则意外度评价方法,并在此基础上设计了基于意外度的深层关联规则挖掘算法。算法的优点在于能够将用户已知的规则作为领域知识加入到数据挖掘过程从而有效过滤和已知规则相近的冗余规则,并且可以将新得到的规则加入知识库中实现知识的积累和重用。最后本文采用一个商场数据验证了该算法的有效性,并且对具有回馈模式的关联规则在商品促销中的作用进行了分析。     

一类表间多层次关联规则挖掘算法研究

关联规则采掘是数据挖掘及其应用研究中的重要内容之一.本文提出了多表间多概念多层次关联规则挖掘问题,研究了相关的挖掘算法,对所提出的算法进行了初步分析.该算法应用于某营销经理信息系统的关联规则挖掘,获得的结果表明算法是实用和有效的.     

一种基于粗糙集理论的规则获取算法

获取规则是数据挖掘中的一项重要技术 ,根据粗糙集理论及决策值归纳函数的概念 ,可以把不相容的决策系统转化为相容的决策系统 ,并提出规则参数的合并方法 .在此基础上 ,利用决策矩阵和决策函数 ,提出了一种在决策系统中获取规则的算法 .同传统的算法相比 ,该算法得出的规则集没有信息丢失的现象发生 .最后以例子作了说明 .     

基于关联规则的网络消费者行为变化的挖掘

在网络购物环境下,消费者需求的变化日渐突出,为了发现网络消费者需求的变化,论文采用关联规则发现的方法对不同时期的商品交易数据进行挖掘,提取了关联规则,通过对规则的比较、分析,发现了网络消费者的行为变化.论文提出了一个包含第一支持度、第二支持度和相对置信度的算法,该算法克服了现有算法无法挖掘具有低频数据项规则的问题,并依据网络消费者行为变化的情况,提出了网络消费者行为变化的三种模式茁壮型、发现型、意外型,以度量网络消费者的行为变化.     

基于领域知识和聚类的关联规则深层知识发现研究

本文针对传统关联规则挖掘算法产生大量冗余规则,提出了对关联规则结果进行二次挖掘,并设计了算法对挖掘出的关联规则进行聚类,然后基于已有领域知识对聚类后的关联规则进行新颖度评价,对于新颖度较高价值较大的关联规则可以存储于领域知识库用于决策使用或再次挖掘过程。该算法有效的减少的规则的数量,提高了规则的新颖性和精确度,对商业应用具有很高的价值。文章最后使用UCI开源数据进行了实验分析,并验证了该算法的有效性。     

二分群体决策规则的序性质研究

Karotkin等发现二分群体决策的加权多数决策规则集具有序性质,但未能解释其原因.文章提出了规则链和规则距离函数的概念,指出当一组决策规则构成规则链时这组规则便具有序性质,从而解释了这一现象.而判断一组规则是否构成规则链则可以通过计算各规则间的规则距离来实现.随后通过对具体实例的分析进一步阐述了得到的结论.     

由频繁项集生成关联规则的深度优先算法

数据挖掘是当前数据库技术领域的重点研究内容,其中关联规则挖掘算法尤为引人注目.目前,关联规则及挖掘算法研究的热点主要是如何提高发现频繁项集的效率,而对如何由频繁项集生成关联规则却很少涉及.对由频繁项集生成关联规则的过程进行改进,将会有效提高生成关联规则的效率.     

一种基于密度的无监督联系发现方法

在数据挖掘过程中,利用K-近邻(KNN)算法搜索新颖节点往往具有一定的局限性和偏差性。针对此问题,本文提出了加权距离和相对密度的概念,采用基于加权距离的相对密度来度量一个对象的局部离群程度。在此基础上,提出了一种基于密度的无监督联系发现方法,并进行了实验。实验结果表明,该方法能够较准确地描述对象的异常程度,具有更高的精确度。     

行业潜规则

华尔街的债券评级机构蒙骗了全世界的投资者用途广泛的三聚氰胺却坑害了全中国消费者百度的竞价排名广告愚弄了全体中文网民无数潜规则大行其道……     

零度创新法则

它在自由状态下产生,既能独立的自主创造,又可以自由地借各种外部精华为我所用,学习模仿借力。这种创新行为,既可能产生于领导者,更可能由企业基层员工参与和推动。     

On Optimal Rules of Persuasion

A speaker wishes to persuade a listener to accept a certain request. The conditions under which the request is justified, from the listener's point of view, depend on the values of two aspects. The values of the aspects are known only to the speaker and the listener can check the value of at most one. A mechanism specifies a set of messages that the speaker can send and a rule that determines the listener's response, namely, which aspect he checks and whether he accepts or rejects the speaker's request. We study mechanisms that maximize the probability that the listener accepts the request when it is justified and rejects the request when it is unjustified, given that the speaker maximizes the probability that his request is accepted. We show that a simple optimal mechanism exists and can be found by solving a linear programming problem in which the set of constraints is derived from what we call the L‐principle.     

Asymptotics for Statistical Treatment Rules

This paper develops asymptotic optimality theory for statistical treatment rules in smooth parametric and semiparametric models. Manski (2000, 2002, 2004) and Dehejia (2005) have argued that the problem of choosing treatments to maximize social welfare is distinct from the point estimation and hypothesis testing problems usually considered in the treatment effects literature, and advocate formal analysis of decision procedures that map empirical data into treatment choices. We develop large‐sample approximations to statistical treatment assignment problems using the limits of experiments framework. We then consider some different loss functions and derive treatment assignment rules that are asymptotically optimal under average and minmax risk criteria.     

Expedient and Monotone Learning Rules

This paper considers learning rules for environments in which little prior and feedback information is available to the decision maker. Two properties of such learning rules are studied: absolute expediency and monotonicity. Both require that some aspect of the decision maker's performance improves from the current period to the next. The paper provides some necessary, and some sufficient conditions for these properties. It turns out that there is a large variety of learning rules that have the properties. However, all learning rules that have these properties are related to the replicator dynamics of evolutionary game theory. For the case in which there are only two actions, it is shown that one of the absolutely expedient learning rules dominates all others.     

The Fairness of Decision Rules

Prior work on resource allocation has generally considered only a small number of allocation rules, usually reflecting equity or equality. We use a scenario study to examine the effect of eight different allocation rules (past performance, future performance, rank, random draw, chance meetings, business need, personal need, and political reasons) on recipient reactions to the gain or loss of three different kinds of resources in an organizational setting. We find evidence that allocations based on past performance and random draw rules lead to the highest fairness perceptions and the lowest expectations that the decisions made will lead to intragroup conflict. However, fairness judgments are also influenced by a variety of other factors, such as the type of resource being allocated and whether the recipient is advantaged or disadvantaged relative to others in the workgroup (what we term the “egocentric interaction”). We discuss how our results might influence managers’ allocation decisions.     

Optimal Abort Rules for Multiattempt Missions

Many real‐world systems use mission aborts to enhance their survivability. Specifically, a mission can be aborted when a certain malfunction condition is met and a risk of a system loss in the case of a mission continuation becomes too high. Usually, the rescue or recovery procedure is initiated upon the mission abort. Previous works have discussed a setting when only one attempt to complete a mission is allowed and this attempt can be aborted. However, missions with a possibility of multiple attempts can occur in different real‐world settings when accomplishing a mission is really important and the cost‐related and the time‐wise restrictions for this are not very severe. The probabilistic model for the multiattempt case is suggested and the tradeoff between the overall mission success probability (MSP) and a system loss probability is discussed. The corresponding optimization problems are formulated. For the considered illustrative example, a detailed sensitivity analysis is performed that shows specifically that even when the system's survival is not so important, mission aborting can be used to maximize the multiattempt MSP.     

Ordinally Bayesian Incentive Compatible Voting Rules

We study strategic voting after weakening the notion of strategy‐proofness to Ordinal Bayesian Incentive Compatibility (OBIC). Under OBIC, truth‐telling is required to maximize the expected utility of every voter, expected utility being computed with respect to the voter's prior beliefs and under the assumption that everybody else is also telling the truth. We show that for a special type of priors, i.e., the uniform priors, there exists a large class of social choice functions that are OBIC. However, for priors that are generic in the set of independent beliefs, a social choice function is OBIC only if it is dictatorial. This result underlines the robustness of the Gibbard–Satterthwaite Theorem.     

Statistical Treatment Rules for Heterogeneous Populations

An important objective of empirical research on treatment response is to provide decision makers with information useful in choosing treatments. This paper studies minimax‐regret treatment choice using the sample data generated by a classical randomized experiment. Consider a utilitarian social planner who must choose among the feasible statistical treatment rules, these being functions that map the sample data and observed covariates of population members into a treatment allocation. If the planner knew the population distribution of treatment response, the optimal treatment rule would maximize mean welfare conditional on all observed covariates. The appropriate use of covariate information is a more subtle matter when only sample data on treatment response are available. I consider the class of conditional empirical success rules; that is, rules assigning persons to treatments that yield the best experimental outcomes conditional on alternative subsets of the observed covariates. I derive a closed‐form bound on the maximum regret of any such rule. Comparison of the bounds for rules that condition on smaller and larger subsets of the covariates yields sufficient sample sizes for productive use of covariate information. When the available sample size exceeds the sufficiency boundary, a planner can be certain that conditioning treatment choice on more covariates is preferable (in terms of minimax regret) to conditioning on fewer covariates.     

新领导如何面对老规矩

中国有一句古话,叫“新官上任三把火”。不论是外面来的新领导,还是内部晋升的新主官,所面对的都是新使命,为了更好地完成自己的工作,总是会或多或少地按照自己的意愿改变单位原有的某些规矩,这些做法是否妥当?对此要辩证地看。新任领导面临着新旧之间的矛盾:老部属对原领导的做事方法已经习以为常,而新领导也有一套长期养成的思维和行事方法,当老部属看到新领导的做事方法和风格与原来的领导不一样时,就会感到不习惯。修养好、忍耐力较强的,即使心里不舒服,嘴上也不会说,还是会按照新领导所说的去做,至多也就是怠工而已;而一些性子急的部属…