Thesis (Ph.D.)--George Mason University, 2008. / Vita: p. 141. Thesis director: Edward J. Wegman. Submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Computational Sciences and Informatics. Title from PDF t.p. (viewed July 3, 2008). Includes bibliographical references (p. 105-110). Also issued in print.

As the deregulation of the mobile number portability (MNP) and the emergence of such new technologies and services as PHS and 3G, the mobile telecommunications industry in Taiwan becomes highly competitive than ever. Under such competition, customer churning and profit declining have become of great concerns to mobile service providers. In response, most of providers continuously develop and introduce new value-added products and services. Frequent value-add products and services might strengthen customers¡¦ loyalty (i.e., decrease customer churning) and improve gross profits, but the corresponding marketing cost would also be increased dramatically. To lower the marketing cost and respond to market quickly, marketing staff typically adopts a pilot test based on the simple random sampling (SRS) approach or relies on marketing experts for defining potential target market for a new value-add product or service. The former approach requires a large number of respondents in the pilot test, while the latter is knowledge intensive and may suffer from unavailability of knowledge due to turnover of experienced marketing experts. In this thesis, we propose a novel approach for efficient and effective search for the target market for a new product/service. Specifically, we consider the target market of a new product or service being that of the most similar existing product/service, where the similarity of products/services can be defined based on either their product/service attributes or the similarity between the pilot test of the new product/service and the customer-base of an existing product/service. Accordingly, we propose two target market prediction models for new product/service, i.e., ¡§customer-based target market prediction model¡¨ and ¡§product-attribute-based target market prediction model.¡¨ Our empirical results show that the proposed prediction models are more effective in predicting potential customers for new products/services than traditional approaches.

Abstract As deregulation and new competitors open up the telecommunications industry, the cellular phone market has become more competitive than ever. To survive or maintain an advantage in such a competitive marketplace, many telecommunications companies are turning to data mining techniques to resolve such challenging issues as fraud detection, customer retention, and prospect profiling. In this thesis, we focused on developing and applying data mining technique to support the churn prediction. Constrained by limited customer profiles and general demographics, the proposed approach applied a decision tree induction technique (i.e., C4.5) to discover a classification model for churn predication solely based on the call records. To deal with the training data with a highly skewed distribution on decisions (i.e., around 2% churners and 98% non-churners), a multi-expert strategy was adopted. The empirical results showed that the proposed technique was effective in predicting at-risk cellular phone customers (i.e., potential churners). The proposed technique could identify 50.64% churners by selecting 10.03% of the population, and 68.62% churners by selecting 29.00% of the population.

Thesis (doctoral)--Universiteit Leiden, 2003. / "Proefschrift." "Complex Streamed Instruction Set (CSI)"--Pref. Includes bibliographical references (p. 142-146).

Many interesting applications involve decision prediction based on a time-series sequence or a set of time-series sequences, which are referred to as time-series classification problems. Past classification analysis research predominately focused on constructing a classification model from training instances whose attributes are atomic and independent. Direct application of traditional classification analysis techniques to time-series classification problems requires the transformation of time-series data into non-time-series data attributes by applying some statistical operations (e.g., average, sum, etc). However, such statistical transformation often results in information loss. In this thesis, we proposed the Time-Series Classification (TSC) technique, based on the nearest neighbor classification approach. The result of empirical evaluation showed that the proposed time-series classification technique had better performance than the statistical-transformation-based approach.