A common problem for marketing strategists is how to appropriately segment the market and select segment-specific marketing strategies. This paper presents a novel approach which integrates Fuzzy Delphi method, self-organizing maps (SOM) and a visualization technique to cluster customers according to their various characteristic variables and visualize segments by producing colorful market maps. These market maps not only help the managers to see fully visualized clusters of market but also reveal mutual non-linear correlations between different customers' characteristic variables. In this research we studied ADSL service market of an Iranian Telecommunication Company. SOM algorithm and visualizing technique were implemented in MATLAB environment to produce market maps of data set.

Visualizing market segmentation using self-organizing maps and Fuzzy Delphi method - ADSL market of a telecommunication company

Highlights? We propose a method for segmentation in retailing, based on customers' lifestyle. ? We identify typical shopping baskets by clustering the transactional records. ? We infer the lifestyle corresponding to each typical shopping basket. ? Customers are assigned to a segment based on the similarity with the typical baskets. ? We identify actions to reinforce the relationship between companies and customers. A good relationship between companies and customers is a crucial factor of competitiveness. Market segmentation is a key issue for companies to develop and maintain loyal relationships with customers as well as to promote the increase of company sales. This paper proposes a method for market segmentation in retailing based on customers' lifestyle, supported by information extracted from a large transactional database. A set of typical shopping baskets are mined from the database, using a variable clustering algorithm, and these are used to infer customers lifestyle. Customers are assigned to a lifestyle segment based on their purchases history. This study is done in collaboration with an European retailing company.

Customer data mining for lifestyle segmentation

https://isiarticles.com/bundles/Article/pre/pdf/17728.pdf

A data mining framework for detecting subscription fraud in telecommunication

This study uses Adaptive Neuro-Fuzzy Inference System (ANFIS) to explore the nonlinear relationships between green innovation performance and corporate competitive advantage. The result indicates that green innovation performance has the nonlinear effect on the corporate competitive advantage. If companies hope to enhance their competitive advantages through green innovation, they must check their green innovation performance in advance. If their green innovation performance is low, they can obtain competitive advantages through the increase of the green innovation performance; however, if their green innovation performance is high, they can not necessarily obtain competitive advantages through the increase of the green innovation performance.

The nonlinear effect of green innovation on the corporate competitive advantage

Background Pharmacists' roles in health care systems are expanding. However, some patients are slow to accept and make use of this expanded role. Objectives The objectives for this study were to identify and describe segments of pharmacists and patients based upon their perceptions of the pharmacist's role in serving as an advisor on medication use. Methods Data were collected from random samples of pharmacists and patients in 1995, 1998, 2001, 2004, 2007, and 2010. Overall, 1518 pharmacists (overall response rate = 47%) and 1278 patients (overall response rate = 42%) were surveyed from 1995 through 2010. Factor analysis was applied to a Counselor Role Orientation measure and identified three factors for use in segmentation analysis. The factors were: (1) Time Pressures, (2) Reliance on Physician, and (3) Pharmacist Restrictions. Segmentation analysis was conducted using a two-step cluster analysis with an agglomerative hierarchical clustering method and a log-likelihood (probability) distance measure. Descriptive statistics were used to describe identified segments. Results Cluster analysis identified four segments which were named: (1) All Low, (2) Time Pressures, (3) Reliance On Physician, and (4) All High. The largest segment for pharmacists was Time Pressures (45% of pharmacists) and for patients was Reliance on Physician (50% of patients). Composition of the four segments was consistent over time between the years 1995 through 2010. Conclusions The pattern of findings suggested a cycle of dysfunction in which many pharmacists, hindered by Time Pressures, do not provide patient care beyond the dispensing of a product. In turn, patients, relying on their physician for advice about medications, do not acknowledge the pharmacist as an advisor for medications. This cycle has reinforced dysfunctional behaviors and creates no motivation for either party in this dyadic relationship to change.

A segmentation analysis for pharmacists' and patients' views of pharmacists' roles

Kohonen's self-organizing map (SOM) network is an unsupervised learning neural network that maps an n-dimensional input data to a lower dimensional output map while maintaining the original topological relations. The extended SOM network further groups the nodes on the output map into a user specified number of clusters. In this research effort, we applied this extended version of SOM networks to a consumer data set from American Telephone and Telegraph Company (AT&T). Results using the AT&T data indicate that the extended SOM network performs better than the two-step procedure that combines factor analysis and K-means cluster analysis in uncovering market segments.

/pdf/an-extended-self-organizing-map-network-for-market-5bkqcuuryp.pdf

Michael Y. Hu

Papers

An extended self-organizing map network for market segmentation: a telecommunication example