In today's information age, companies collect massive amount of asymmetric flow data at individual customer level. Examples include customer-by-customer data (e.g., money, phone call and email flows among customers), product-by-product data (e.g., sequential purchase data), and web traffic data, etc. Asymmetric flow data carries meaningful customer intelligence and yet, it is under-explored. When combined with other data (such as customer profile and sales, etc.), this flow data can provide valuable understanding on individual customers, and thus enable marketers to trigger marketing actions at individual-customer level. / Simulation results show that the proposed algorithms yield promising model fitting performance within reasonable time. The LAS algorithm can successfully analyze 100,000 subjects in less than 10 hours. The CAS algorithm analyzes 50,000 subjects in 18 hours. The TAS algorithm analyzes 5,000 subjects within one hour. The proposed models are also applied on two real datasets (i.e., email data and web log data) to investigate the network structure among researchers and web pages. Results of simulation experiments and real data analyses suggest the proposed asymmetric scaling methods are viable ways of analyzing massive asymmetric flow data in marketing. / This thesis proposes three asymmetric scaling methods to analyze asymmetric flow data in marketing, namely Linear Asymmetric Scaling (LAS), Circular Asymmetric Scaling (CAS), and Two-dimensional Asymmetric Scaling (TAS). To visualize and analyze the asymmetric relationship among subjects, we assume that each subject has two relationship roles (i.e., as a source and as a destination of relationship flows). The LAS, CAS and TAS models represent asymmetric relationship among subjects by linear, circular and two-dimensional representations respectively. / Ho Ying. / "February 2007." / Adviser: Kin-Nam Lau. / Source: Dissertation Abstracts International, Volume: 68-09, Section: A, page: 3969. / Thesis (Ph.D.)--Chinese University of Hong Kong, 2007. / Includes bibliographical references (p. 230-241). / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Electronic reproduction. [Ann Arbor, MI] : ProQuest Information and Learning, [200-] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Electronic reproduction. Ann Arbor, MI : ProQuest dissertations and theses, [201-] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Abstract in English and Chinese. / School code: 1307.

No description available.

published_or_final_version / Mathematics / Master / Master of Philosophy

Thesis (M.S.)--Massachusetts Institute of Technology, Alfred P. Sloan School of Management, 1981. / MICROFICHE COPY AVAILABLE IN ARCHIVES AND DEWEY. / Bibliography: leaves 101-104. / by Michael Joseph Horn. / M.S.

by Ka-Kit Tse. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1997. / Includes bibliographical references. / Acknowledgments --- p.i / List of tables --- p.v / Chapter Chapter 1: --- Overall Review --- p.1 / Chapter Chapter 2: --- Essay one - A Mathematical Programming Approach to Clusterwise Regression Model and its Extensions / Chapter 2.0. --- Abstract --- p.5 / Chapter 2.1. --- Introduction --- p.6 / Chapter 2.2. --- A Mathematical Programming Formulation of the Clusterwise Regression Model --- p.10 / Chapter 2.2.1. --- The Generalized Clusterwise Regression Model --- p.10 / Chapter 2.2.2. --- "Clusterwise Regression Model (Spath, 1979)" --- p.14 / Chapter 2.2.3. --- A Nonparametric Clusterwise Regression Model --- p.15 / Chapter 2.2.4. --- A Mixture Approach to Clusterwise Regression Model --- p.16 / Chapter 2.2.5. --- An Illustrative Application --- p.19 / Chapter 2.3. --- Mathematical Programming Formulation of the Clusterwise Discriminant Analysis --- p.21 / Chapter 2.4. --- Conclusion --- p.25 / Chapter 2.5. --- Appendix --- p.28 / Chapter 2.6. --- References --- p.32 / Chapter 2.7. --- Tables --- p.35 / Chapter Chapter 3: --- Essay two - A Mathematical Programming Approach to Clusterwise Rank Order Logit Model / Chapter 3.0. --- Abstract --- p.40 / Chapter 3.1. --- Introduction --- p.41 / Chapter 3.2. --- Clusterwise Rank Order Logit Model --- p.42 / Chapter 3.3. --- Numerical Illustration --- p.46 / Chapter 3.4. --- Conclustion --- p.48 / Chapter 3.5. --- References --- p.50 / Chapter 3.6. --- Tables --- p.52 / Chapter Chapter 4: --- Essay three - A Mathematical Programming Approach to Metric Unidimensional Scaling / Chapter 4.0. --- Abstract --- p.53 / Chapter 4.1. --- Introduction --- p.54 / Chapter 4.2. --- Nonlinear Programming Formulation --- p.56 / Chapter 4.3. --- Numerical Examples --- p.60 / Chapter 4.4. --- Possible Extensions --- p.61 / Chapter 4.5. --- Conclusion and Extensions --- p.63 / Chapter 4.6. --- References --- p.64 / Chapter 4.7. --- Tables --- p.66 / Chapter Chapter 5: --- Research Project in Progress / Chapter 5.1. --- Project 1 -- An Integrated Approach to Taste Test Experiment Within the Prospect Theory Framework --- p.68 / Chapter 5.1.1. --- Experiment Procedure --- p.68 / Chapter 5.1.2. --- Experimental Result --- p.72 / Chapter 5.2. --- Project 2 -- An Integrated Approach to Multi- Dimensional Scaling Problem --- p.75 / Chapter 5.2.1. --- Introduction --- p.75 / Chapter 5.2.2. --- Experiment Procedure --- p.76 / Chapter 5.2.3. --- Questionnaire --- p.78 / Chapter 5.2.4. --- Experimental Result --- p.78

No description available.

Spatial competition, in the context of industry-wide changes in retailing formats and strategies, is addressed in this dissertation from a theoretical modelling perspective. Chapter2 develops a normative individual choice model to explore how "power retailers" affect grocery shopping behaviour, and, consequently, market share. Power retailers are very large retail outlets that compete primarily on price, and are known variously as warehouse clubs, category killers, and superstores. The model shows that consideration of consumer stockpiling can lead to an "increasing returns" nonlinear response of market share to price reductions, and that the effect is not noticeable when competitors have small price differences. The model also differentiates between perishable and nonperishable goods, and shows that this may drive planned multistore shopping. Chapter 3 starts with the observation that competent management in many sectors of retailing, including grocery retailing, requires an ability to respond quickly and effectively to unexpected adversity. This dynamic is included in an oligopolistic spatial interaction model, and the system is shown to evolve to a novel and robust stochastic steady state known as self-organized criticality (SOC). One characteristic of the SOC state is that it allows small exogenous shocks to produce large responses at a rate greater than would be expected if the law of large numbers applied. This work represents the first known investigation of SOC in a marketing setting.

Spatial competition, in the context of industry-wide changes in retailing formats and strategies, is addressed in this dissertation from a theoretical modelling perspective. Chapter2 develops a normative individual choice model to explore how "power retailers" affect grocery shopping behaviour, and, consequently, market share. Power retailers are very large retail outlets that compete primarily on price, and are known variously as warehouse clubs, category killers, and superstores. The model shows that consideration of consumer stockpiling can lead to an "increasing returns" nonlinear response of market share to price reductions, and that the effect is not noticeable when competitors have small price differences. The model also differentiates between perishable and nonperishable goods, and shows that this may drive planned multistore shopping. Chapter 3 starts with the observation that competent management in many sectors of retailing, including grocery retailing, requires an ability to respond quickly and effectively to unexpected adversity. This dynamic is included in an oligopolistic spatial interaction model, and the system is shown to evolve to a novel and robust stochastic steady state known as self-organized criticality (SOC). One characteristic of the SOC state is that it allows small exogenous shocks to produce large responses at a rate greater than would be expected if the law of large numbers applied. This work represents the first known investigation of SOC in a marketing setting. / Business, Sauder School of / Graduate

The market model, which relates securities returns to their systematic risk (β), plays a major role in finance. The estimation of β , in particular, is fundamental to many empirical studies and investment decisions. This dissertation develops a model which explains the observed serial correlations in returns and the intervaling effects which are inconsistent with the market model assumptions. The model accounts for thin trading and different frictions in the trading process and has as special cases other models of thin trading and frictions presented in the finance literature. The main assumption of the model is that the prices observed in the market and used to compute returns differ by an error from the true prices generated by a Geometric Brownian Motion model, hence its name, the error in prices (EIP) model. Three estimation methods for β are examined for the EIP model: the Maximum Likelihood (ML) method, the Least Squares (LS) method and a method of moments. It is suggested to view the EIP model as a missing information model and use the EM algorithm to find the ML estimates of the parameters of the model. The approximate small sample and asymptotic properties of the LS estimate of β are derived. It is shown that replacing the true covariances by their sample moments estimates leads to a convenient and familiar form for a consistent estimate of β. Finally, some illustrations of six different estimation methods for β are presented using simulated and real securities returns. / Business, Sauder School of / Graduate

A computer-based analog model to determine market potential for electric power-driven water pumps in developing countries. The purpose of this study is to develop a computer-based model that predicts the market potential for electric water pumps in developing nations.The logic employed in such an analysis first seeks out countries which at some point in their recent history have exhibited unusually high growth rates in aggregate pump demand during a period of several years. Next, the researcher evaluates the significance of specific social and economic "indicator" variables when matched with raw trade statistics for that country via stepwise regression--a computer assisted procedure. Finally, by isolating the economic and/or social factors that most closely parallel a country's pump demand, one can identify and rank the developing countries offering the greatest potential sales. The systematically chosen highpotential markets are then worthy of individual consideration and additional resource contribution in a given firm's strategic marketing plan.Since reach of the data were locally unavailable, a trip to the Department of Com©erce in Washington, D.C. and the United Nations in New York City was required. Funding to proceed with Part III of this report was solicited from, and granted by, a major domestic producer of electric water pump motors.The results of the research identified eight indicator variables directly correlated to the demand for imported pumps in developing nations. The regression equation composed of these eight variables, then, will be accepted as the best available model for predicting a country's pumpdemand. The regression equation also shows that each of the eight indicator variables contributes to changes in pump demand in different magnitudes.The research has identified forty-four developing nations with significant growth-rates in one or more of the eight indicator variables. Market projections are finally derived by comparing an individual country's indicator variable growth-rate to its historical pump demand growth-rate.