by Fong Kwan-ting, Ronald, Koo Cheuk-wah, Anthony. / Thesis (M.B.A.)--Chinese University of Hong Kong, 1994. / Includes bibliographical references (leaves 56-58). / ACKNOWLEDGEMENT --- p.i / ABSTRACT --- p.ii / TABLE OF CONTENTS --- p.iii / LIST OF FIGURES --- p.v / LIST OF EXHIBITS --- p.vi / Chapter / Chapter I. --- INTRODUCTION --- p.1 / Objective of this Project --- p.2 / Planning and Allocating Resources --- p.2 / Controliing Operations --- p.3 / Evaluating the Performance of Segment Managers --- p.3 / Background of C&P Company -- a Hypothetical Case --- p.3 / Chapter II. --- LITERATURE REVIEW --- p.5 / Marketing Performance Assessment --- p.5 / Marketing Efficiency --- p.6 / Marketing Effectiveness --- p.7 / Marketing audit --- p.7 / Marketing effectiveness --- p.9 / Recent Developments of Marketing Performance Assessment --- p.10 / Concluding Remarks --- p.13 / Segmental Contribution Analysis --- p.14 / Terminologies Used in Segmental Contribution Analysis --- p.14 / Direct fixed costs --- p.14 / Common fixed costs- --- p.15 / Contribution margin --- p.15 / Performance margin --- p.15 / Segment margin --- p.15 / Residual income analysis --- p.16 / Net income --- p.16 / Segmental Contribution Accounting System --- p.16 / Application of the Proposed Segmental Contribution Accounting System --- p.18 / Contribution margin --- p.18 / Segment margin --- p.18 / Evaluating segment manager's performance --- p.19 / Concluding Remarks --- p.19 / Chapter III. --- SYSTEM DESIGN FOR THE C&P COMPANY --- p.21 / Prototype --- p.21 / Input Formats --- p.21 / Output Formats --- p.22 / Structure Analysis --- p.22 / Data Flow Diagram --- p.22 / System Dictionary --- p.23 / Transform Descriptions --- p.23 / Chapter IV. --- CONCLUSION & DIRECTION FOR FUTURE RESEARCH --- p.24 / EXHIBITS --- p.25 / BIBLIOGRAPHY --- p.56

Este trabalho explora a contribuição da segmentação de dados, manual e estatística, combinada com análise discriminante e com redes neurais, para a tomada de decisão de concessão de crédito ao consumidor. A grande importância que a decisão de concessão de crédito tem para o mercado varejista e para a área de controladoria de uma empresa dão cenário para o aumento da relevância do gerenciamento do risco de crédito. O mercado necessita, cada vez mais, de modelos capazes de produzir boas expectativas do comportamento dos clientes, com vistas de reduzir perdas com inadimplência. Dado um banco de dados composto por 50 mil clientes de uma importante loja do setor varejista, primeiro aplica-se a análise discriminante, depois as redes neurais, para que se classifique a capacidade preditiva de cada técnica nesta etapa. Posteriormente, os dados são segmentados com base na região à qual a filial de venda pertence e, depois, por meio das análises de clusters K-Means e TwoStep Cluster. A próxima etapa compreende a aplicação da análise discriminante, depois das redes neurais, para cada um dos grupos formados, tanto pela segregação por região, quanto pela segregação por meio das técnicas de análise de clusters. A última etapa abrange a comparação da soma dos acertos dos bons e dos maus pagadores obtida tanto para análise discriminante, quanto para redes neurais, combinadas com a segmentação de dados, com os resultados obtidos na primeira etapa sem a segmentação dos dados. O modelo híbrido que combina a segmentação manual dos dados com análise discriminante e com redes neurais, formando-se 21 micro-regiões foi o que apresentou maiores porcentagens de acerto de classificação. O modelo híbrido que combina análise discriminante e redes neurais com a análise de clusters TwoStep Cluster não apresenta resultados de classificação adequados à proposta deste trabalho, devendo, portanto, ser descartado. / This paper explores the contribution of data segmentation, and statistical manual, combined with discriminant analysis and neural networks, for making the decision to grant credit to consumers. The great importance that the decision to grant credit is for the retail market and the area of controlling a business scenario to give increasing importance of managing credit risk. The market needs, increasingly, models capable of producing good expectations of customer behavior, in order to reduce losses from default. Given a database consisting of 50 000 customers of a major retail store, the first applies to discriminant analysis, then the neural networks, in order to classify the predictive ability of each technique in this step. Subsequently, the data are segmented based on the region to which the branch belongs to sell and then through the analysis of clusters K-Means and TwoStep Cluster. The next step involves the application of discriminant analysis, neural networks then, for each of the groups formed by both the segregation by region, by segregation and by the techniques of cluster analysis. The last step includes comparing the sum of the hits of the good and bad debtors obtained for both discriminant analysis and neural networks, combined with the segmentation of data, with the results obtained in the first stage - without the segmentation of the data. The hybrid model that combines the manual segmentation of the data with discriminant analysis and neural networks, forming 21 micro-regions showed the highest percentage of correct classification. The hybrid model that combines neural networks and discriminant analysis with cluster analysis results TwoStep Cluster does not have appropriate rating to the proposal of this work and should therefore be discarded.

Este trabalho explora a contribuição da segmentação de dados, manual e estatística, combinada com análise discriminante e com redes neurais, para a tomada de decisão de concessão de crédito ao consumidor. A grande importância que a decisão de concessão de crédito tem para o mercado varejista e para a área de controladoria de uma empresa dão cenário para o aumento da relevância do gerenciamento do risco de crédito. O mercado necessita, cada vez mais, de modelos capazes de produzir boas expectativas do comportamento dos clientes, com vistas de reduzir perdas com inadimplência. Dado um banco de dados composto por 50 mil clientes de uma importante loja do setor varejista, primeiro aplica-se a análise discriminante, depois as redes neurais, para que se classifique a capacidade preditiva de cada técnica nesta etapa. Posteriormente, os dados são segmentados com base na região à qual a filial de venda pertence e, depois, por meio das análises de clusters K-Means e TwoStep Cluster. A próxima etapa compreende a aplicação da análise discriminante, depois das redes neurais, para cada um dos grupos formados, tanto pela segregação por região, quanto pela segregação por meio das técnicas de análise de clusters. A última etapa abrange a comparação da soma dos acertos dos bons e dos maus pagadores obtida tanto para análise discriminante, quanto para redes neurais, combinadas com a segmentação de dados, com os resultados obtidos na primeira etapa sem a segmentação dos dados. O modelo híbrido que combina a segmentação manual dos dados com análise discriminante e com redes neurais, formando-se 21 micro-regiões foi o que apresentou maiores porcentagens de acerto de classificação. O modelo híbrido que combina análise discriminante e redes neurais com a análise de clusters TwoStep Cluster não apresenta resultados de classificação adequados à proposta deste trabalho, devendo, portanto, ser descartado. / This paper explores the contribution of data segmentation, and statistical manual, combined with discriminant analysis and neural networks, for making the decision to grant credit to consumers. The great importance that the decision to grant credit is for the retail market and the area of controlling a business scenario to give increasing importance of managing credit risk. The market needs, increasingly, models capable of producing good expectations of customer behavior, in order to reduce losses from default. Given a database consisting of 50 000 customers of a major retail store, the first applies to discriminant analysis, then the neural networks, in order to classify the predictive ability of each technique in this step. Subsequently, the data are segmented based on the region to which the branch belongs to sell and then through the analysis of clusters K-Means and TwoStep Cluster. The next step involves the application of discriminant analysis, neural networks then, for each of the groups formed by both the segregation by region, by segregation and by the techniques of cluster analysis. The last step includes comparing the sum of the hits of the good and bad debtors obtained for both discriminant analysis and neural networks, combined with the segmentation of data, with the results obtained in the first stage - without the segmentation of the data. The hybrid model that combines the manual segmentation of the data with discriminant analysis and neural networks, forming 21 micro-regions showed the highest percentage of correct classification. The hybrid model that combines neural networks and discriminant analysis with cluster analysis results TwoStep Cluster does not have appropriate rating to the proposal of this work and should therefore be discarded.

Segmentation of human head on medical images is an important process in a wide array of applications such as diagnosis, facial surgery planning, prosthesis design, and forensic identification. In this study, a new Bayesian method for segmentation of facial tissues is presented. Segmentation classes include muscle, bone, fat, air and skin. The method incorporates a model to account for image blurring during data acquisition, a prior helping to reduce noise as well as a partial volume model. Regularization based on isotropic and directional Markov Random Field priors are integrated to the algorithm and their effects on segmentation accuracy are investigated. The Bayesian model is solved iteratively yielding tissue class labels at every voxel of an image. Sub-methods as variations of the main method are generated by switching on/off a combination of the models. Testing of the sub-methods are performed on two patients using single modality three-dimensional (3D) images as well as registered multi-modal 3D images (Magnetic Resonance and Computerized Tomography). Numerical, visual and statistical analyses of the methods are conducted. Improved segmentation accuracy is obtained through the use of the proposed image models and multi-modal data. The methods are also compared with the Level Set method and an adaptive Bayesiansegmentation method proposed in a previous study.

This thesis aims to give a comprehensive account of some of the most recent methods of a change point estimation. The literature on the change point estimation shows a variety of approaches to deal with this subject. Among them, tests based on the popular CUSUM process, likelihood ratio tests, wild binary segmentation and some of the most recent techniques on the change point estimation in panel data are all covered by this paper. The case of dependent panels is discussed as well. The practical part of the study is focused on application of the wild binary segmentation method on weekly log-returns of the Dow Jones stock index. Firstly, we fit a GARCH model to the analysed time series. We next use the wild binary segmenatation method to detect structural changes in the mean of the original time series. Next, we apply the same method to the residuals from the GARCH fit. We analyse several penalization criteria proposed by previous studies and evaluate their effects on the estimated number and locations of the change points in the given data set. 1