The Myth of Enterprise Database Redesign

This chapter illustrates how IT-enabled business process reengineering can fail if top management fails to understand the underlying process problems and limitations of data-centric enterprise software. Vicro Communications (we use a pseudonym to mask the organization’s name) attempted to reengineer its basic business processes with the aid of data-centric enterprise software. Vicro management however made the mistake of relying completely on enterprise software to improve the performance of its business processes. It was hoped that the software would increase information sharing, process efficiency, standardization of IT platforms, and data mining/warehousing capabilities. Management however made no attempt to rethink existing processes before embarking on a very expensive implementation of the software. Unfortunately for Vicro, the reengineering effort failed miserably even after investing hundreds of millions of dollars in software implementation. As a result, performance was not improved and the software is being phased out. By using a phenomenological approach, we were able to socially construct the events surrounding the case to gain a rich understanding of what really happened. From deep analysis, we were able to develop emergent theory about a set of factors influencing enterprise database integration success.

A Telecommunications Model for Managing Complexity of Voice and Data Networks and Services

The telecommunications industry (TI) is challenged by a significant increase in the complexity of information transfer due to a recent proliferation of data mining technologies, techniques and applications. As the result, TI is facing a fundamental paradigm shift, with the convergence of voice and data services as well as ever expanding technologies to its users. This technological movement towards a convergence of telephony and computer technologies, web-based networks, and wired and wireless services is creating areas of tremendous opportunities. These areas of opportunity are for continuous quality improvements and applications of the voice and data convergence mining techniques and their implementations. The TI’s implementation of the data mining algorithms reduces information overload, increases data integrity and accuracy, and effectively manages its global networks.

Frontier Versus Ordinary Regression Models for Data Mining

Frontier Regression Models seek to explain boundary, frontier or optimal behavior rather than average behavior as in ordinary regression models. Ordinary regression is one of the most important tools for data mining. Frontier models may be desirable alternatives in many circumstances. In this chapter, we discuss frontier regression models and compare their interpretations to ordinary regression models. Occasional contact with stochastic frontier estimation models is also made, but we concentrate primarily on pure ceiling or floor frontier models. We also propose some guidelines for when to choose between them.

Combination Forecasts Based on Markov Chain Monte Carlo Estimation of the Mode

This chapter proposes an approach to the combination of forecasts from a new perspective and uses a new estimation methodology. Concepts from optimization and statistics are combined in order to cast the problem as one of estimating the minimizer of a loss function, which is assumed to be not explicitly known. Using weak assumptions on the unknown loss function, and on the performance distribution of the experts, a density for the expert estimates may be derived. Sufficient conditions are then obtained for reducing the problem to that of statistical mode estimation. By regarding individual forecasts as expert estimates of the minimizer of the decision maker’s loss function, the mode of these forecasts becomes a combination forecast. Using the Bayesian approach and the Markov chain Monte Carlo method, an empirical distribution corresponding to the predictive density of the expert estimates can be constructed. Hence the mode can be estimated and a probability interval for the forecast value can also be obtained. The probability interval associated with a combination forecast has not previously been studied in the literature. Thus, the construction of the probability interval is a new contribution. Simulation studies as well as an empirical example are presented to illustrate our method.

New Information Technologies and Other Pertinent Issues Impacting the Strategic Dimension of CRM for Business Excellence

Recent interest in relationship management and relationship marketing has led many firms to consider how to improve customer retention rates. The scope of the current chapter will be limited to an exploratory study of the technologies and relevant issues in the development and deployment of customer relationship management (CRM) applications for businesses, specifically those that would pertain towards impacting the strategic dimension of business and enable them to excel in delivering optimal solutions to customers. Future areas of research in CRM will be identified based on the literature review and observed trends in the subject matter. Based on available technologies, current issues in CRM and other pertinent issues, a conclusion will be drawn reflecting the authors’ opinion.

A Proposed Process for Performing Data Mining Projects

There is an enormous amount of data generated by academic, business, and governmental organizations alike; however, only a small portion of the data that is collected and stored in databases is ever analyzed. Since data are the building blocks for both information and knowledge, the opportunity costs (to organizations) of ignoring data assets can range from competitive disadvantage to organizational demise. Data mining has thus emerged as a discipline focusing on unleashing the potential of data in organizations. The enthusiasm surrounding data mining at large continues to grow; however, at the same time, there are claims that data mining projects fail in delivering the expected value. Many of the causes of the failures can be traced back to strategy, process and technology variables. The purpose of this chapter is to discover a process for performing data mining projects and to propose this process to practitioners as a starting point when making decisions about planning, organizing, executing and closing data mining projects. Literature on package implementation, rapid application development and new product development together with results from a case study are used to arrive at the proposed data mining process. More research is needed to evaluate, refine and validate the proposed process before it can be used as the basis for developing a comprehensive methodology for performing data mining projects.

An Evolutionary Misclassification Cost Minimization Approach for Medical Diagnosis

This chapter illustrates how a misclassification cost matrix can be incorporated into an evolutionary classification system for medical diagnosis. Most classification systems for medical diagnosis have attempted to minimize the misclassifications (or maximize correctly classified cases). The minimizing misclassification approach assumes that Type I and Type II error costs for misclassification are equal. There is evidence that these costs are not equal and incorporating costs into classification systems can lead to superior outcomes. We use principles of evolution to develop and test a genetic algorithm (GA) based approach that incorporates the asymmetric Type I and Type II error costs. Using simulated and real-life medical data, we show that the proposed approach, incorporating Type I and Type II misclassification costs, results in lower misclassification costs than LDA and GA approaches that do not incorporate these costs.

Connectionist and Evolutionary Models for Learning, Discovering and Forecasting Software Effort

Mining information and knowledge from very large databases is recognized as a key research area in machine learning and expert systems. In the current research, we use connectionist and evolutionary models for learning software effort. Specifically, we use these models to learn the software effort from a set of training data set containing information on software projects and test the performance of the model on a holdout sample. The design issues of developing connectionist and evolutionary models for mining software effort patterns on a data set are described. Our research indicates that connectionist and evolutionary models, whenever carefully designed, hold a great promise for knowledge discovery and forecasting software effort.

Bayesian Networks as a Decision Support Tool in Credit Scoring Domain

The main purpose of this article is to discuss applicability of Bayesian belief networks (BBN) within the procedures of working-capital credit scoring conducted in commercial banks. A brief description of Bayesian formulation of causal dependence and its strength is given. Inferential and diagnostic features of BBN are illustrated using sample structure. As an example we present and compare results of estimating a credit risk using two techniques: traditional credit-scoring system and BBN structure.

Data Mining for Optimal Combination Demand Forecasts

This chapter is a case study in combining forecasts for inventory management in which the need for data mining in combination forecasts is necessary. The need comes from selection of sample items on which forecasting strategy can be made for all items, selection of constituent forecasts to be combined and selection of weighting method for the combination. A leading bank in Hong Kong consumes more than 300 kinds of printed forms for its daily operations. A major problem of its inventory control system for such forms management is to forecast their monthly demand. The bank currently uses simple forecasting methods such as simple moving average and simple exponential smoothing for its inventory demands. In this research, the individual forecasts come from well-established time series models. The weights for combination are estimated with quadratic programming. The combined forecast is found to perform better than any of the individual forecasts. Some insights in data mining for this context are obtained.