数据开采的数据质量问题

数据质量是影响数据开采效果的重要因素,这个问题并未受到人们的充分重视.本文针对数据质量在数据开采中的地位,给出了数据质量评价的几个主要尺度.并且结合统计学和机器学习的理论,分析了解决数据质量的方法,强调提高数据质量的出发点在于控制数据源的质量.     

Computer models for corporate planning

This paper presents results of a survey of corporate modelling in 65 U.K. companies. It shows that corporate models were already used in a wide range of industries by 1973 and analyses the characteristics of these models, the uses to which they were put, the background of the model builders, approaches to development of models that were adopted, costs of development, and indications of success or failure. It is, for instance, shown that many corporate models are relatively small and simple, and have been built by accountants, planners and other ultimate users, using special facilities for corporate modelling offered by computer bureaux and consultants.     

An Enhanced Data Perturbation Approach for Small Data Sets

As modern organizations gather, analyze, and share large quantities of data, issues of privacy, and confidentiality are becoming increasingly important. Perturbation methods are used to protect confidentiality when confidential, numerical data are shared or disseminated for analysis. Unfortunately, existing perturbation methods are not suitable for protecting small data sets. With small data sets, existing perturbation methods result in reduced protection against disclosure risk due to sampling error. Sampling error may also produce different results from the analysis of perturbed data compared to the original data, reducing data utility. In this study, we develop an enhancement of an existing perturbation technique, General Additive Data Perturbation, that can be used to effectively mask both large and small data sets. The proposed enhancement minimizes the risk of disclosure while ensuring that the results of commonly performed statistical analyses are identical and equal for both the original and the perturbed data.     

Planning models for budgeting teaching resources

This paper relates experience in the development of a set of integrated planning models for a school board in a public school system. Three modules were developed. An enrolment projection module utilizes a modified Markov transition matrix (augmented by adaptive exponential smoothing models to forecast flows into the system). A program review module operates in interactive mode as a deterministic simulation to generate alternative budgets in a ‘planning-programming-budgeting’ context. A resource planning module was produced as an optimizing goal programming formulation, but was not found useful to implement for reasons outlined in the paper.     

Discrete models/continuous models

Continuous approximations are useful in formulating models that humans can comprehend. Discrete approximations are useful in formulating models that computers can “comprehend”. Applications of discrete and continuous approximations are illustrated with examples.     

Deterministic models for premature and postponed replacement

We examine the possibilities of premature and postponed replacement in a deterministic infinite horizon model when there is technological progress. Both revenue and operating cost deteriorate with age, but at different rates. The optimal deterministic replacement time is an implicit solution from the timing boundary obtained for the equivalent real option model using a dynamic programming framework, and then by setting the underlying volatilities equal to zero. A step change improvement characterizing technological progress in the initial operating cost level for the successor occurring during the economic lifetime of the incumbent justifies premature replacement, compared to the traditional present value approach. This finding can be extended to step change improvements in the initial revenue level for the successor and for the re-investment cost. In contrast, if the technological progress can be characterized by a constant declining rate for the initial operating cost level for the successor, then the replacement is postponed for certain parameter values. This finding can be extended to different assumed improvement rates in the initial revenue level for the successor and for the re-investment cost.     

Quantitative models for optimal rest period scheduling

Mathematical and simulation models studying work-rest schedules in a production process are developed to arrive at an optimal rest policy to maximize work output per unit time. A CSMP simulation study is used to test the sensitivity of the results for different specific cases.     

A simple procedure for price break models

This note deals with the problem of determining the economic order quantity of an inventory item having quantity discounts. A simple procedure is suggested which very often reduces the number of computations required for obtaining the economic operating policy.     

Deterministic models for premature and postponed replacement

We examine the possibilities of premature and postponed replacement in a deterministic infinite horizon model when there is technological progress. Both revenue and operating cost deteriorate with age, but at different rates. The optimal deterministic replacement time is an implicit solution from the timing boundary obtained for the equivalent real option model using a dynamic programming framework, and then by setting the underlying volatilities equal to zero. A step change improvement characterizing technological progress in the initial operating cost level for the successor occurring during the economic lifetime of the incumbent justifies premature replacement, compared to the traditional present value approach. This finding can be extended to step change improvements in the initial revenue level for the successor and for the re-investment cost. In contrast, if the technological progress can be characterized by a constant declining rate for the initial operating cost level for the successor, then the replacement is postponed for certain parameter values. This finding can be extended to different assumed improvement rates in the initial revenue level for the successor and for the re-investment cost.     

The robustness of linear models for decision-making

This paper elaborates on some issues discussed by Moskowitz, who presented evidence that linear multiple regression models, estimated from decisions made by individuals, often outperform the individuals themselves. In discussing his results, Moskowitz (1) suggested that inconsistency in information utilization by individuals may account for the relative superiority of regression models, and (2) expressed concern over the robustness of linear regression models to changes in (a) information environments, (b) weighting parameters, and (c) functional form of the model. This paper discusses reasons (in addition to inconsistency) for the relative superiority of model over man, and it summarizes recent research in psychology concerning the robustness of linear regression models (and linear models in general). This paper is supportive, rather than critical, of Moskowitz's research.     

Performance models for unreliable flexible manufacturing systems

This paper deals with the analysis and application of queueing models for single and multi stage flexible manufacturing systems that are subject to resource failure. Exact results are derived for the single stage queueing system. Two approximations are presneted for the multi stage queueing system as a closed network. We validate the approximations by comparing their performance estimates against the exact global balance solution.     

DEA models for extended two-stage network structures

Liang et al. (2008) [1] developed DEA models based upon game approach to decompose efficiency for two-stage network structures where all outputs of the first stage are the only inputs to the second stage. This paper extends Liang et al. (2008) [1] by assuming that the inputs to the second stage include both the outputs from the first stage and additional inputs to the second stage. Two models are proposed to evaluate the performance of this type general two-stage network structures. One is a non-linear centralized model whose global optimal solutions can be estimated using a heuristic search procedure. The other is a non-cooperative model, in which one of the stages is regarded as the leader and the other is the follower. The newly developed models are applied to a case of regional R&D of China.     

An efficient approach for large scale graph partitioning

In this paper, we consider the problem of partitioning the set of vertices of a graph intok subsets of approximately the same cardinality in such a way that the number of edges whose endpoints are in different subsets is minimized. A greedy heuristic, called Procedure1, based on the independent growth of each subset by fronts is proposed for constructing a good-quality graph partition. In addition, we present a more sophisticated version of the greedy heuristic, called Procedure2, which periodically calls a routine to refine the partition being built. We show that the partitions generated by Procedure1 are competitive with those obtained by several constructive heuristics in the literature, e.g. spectral, geometric, as well as other greedy heuristics. Moreover, the partitions produced by Procedure2 are compared with those produced by a leading graph partitioning method in the literature.     

数据挖掘技术在电信CRM中的应用

在介绍数据挖掘技术和客户关系管理概念的基础上,以电信行业为背景,介绍了将数据挖掘技术应用到客户关系管理中的流程和方法,最后以一个案例说明了数据挖掘技术是如何在企业的经营分析中发挥作用的.