تجزیه و تحلیل خوشه ای در تقسیم بندی بازار صنعتی از طریق شبکه عصبی مصنوعی
|کد مقاله||سال انتشار||مقاله انگلیسی||ترجمه فارسی||تعداد کلمات|
|22816||2002||9 صفحه PDF||سفارش دهید||3405 کلمه|
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : Computers & Industrial Engineering, Volume 42, Issues 2–4, 11 April 2002, Pages 391–399
Market segmentation has commonly applied cluster analysis. This study intends to make the comparison of conventional two-stage method with proposed two-stage method through the simulated data. The proposed two-stage method is the combination of self-organizing feature maps and K-means method. The simulation results show that the proposed scheme is better than the conventional two-stage method based on the rate of misclassification.
Wendal Smith presented the concept of market segmentation in 1956. It has become one of the fundamental concepts of marketing (Smith, 1956). By following the market segmentation strategy, a firm could increase the expected profits. Though a number of market segmentation methods have been presented to solve this problem for many decades, the advancement of market segmentation research requires narrowing the gap between the academically oriented research on segmentation and real-world application of segmentation research (Wind, 1978). Thus, this study is intended to propose a new two-stage scheme by integrating ANN and multivariate analysis, though a two-stage method was suggested by Punj and Steward (1983). At that time, the two-stage method consists of a hierarchical method, like Ward's minimum variance method, and followed by a non-hierarchical method, such as K-means method. In the current study, a modified two-stage method, which first uses the self-organizing feature maps to determine the number of clusters and the starting point and then employs the K-means method to find the final solution, is proposed. The numerical simulation data are applied to validate the feasibility of the proposed method. The simulation results show that the proposed two-stage method is more accurate than the conventional two-stage method (Ward's minimum variance method followed by K-means method) based on the rate of misclassification. The rest of this paper is organized as follows. Section 2 presents the general idea of market segmentation and applications of ANNs in marketing segmentation, while the proposed two-stage method is explained in Section 3. Section 4 shows the simulation algorithm and results. Finally, the concluding remarks are made in Section 5.
نتیجه گیری انگلیسی
This study has presented a novel two-stage scheme for market segmentation. The simulated data has illustrated that the proposed two-stage clustering method is slightly better than the conventional two-stage method, though the paired-sample t-test indicates that there is no significant difference. In this study, the self-organizing feature maps are utilized to determine the number of clusters. However, in some cases, it is quite difficult to determine the cluster number by observing the outcome of network output array, unless the network topology is very clear. Therefore, it may be desirable to apply different unsupervised neural networks, like ART-2, for further comparison (Wann and Thomopoulos, 1997). Besides, we can observe whether the difference exists or not if fuzzy C-means method replaces the K-means method. Also, genetic algorithm has been shown quite promising in many areas. Thus, it is possible to employ genetic algorithm for clustering.