資料採礦應用於通路區隔與產品區隔之研究

The study of data mining approach implements on the channel and product segmentation

楊小微(Hsiao-Wei Yang)

指導教授 ： 廖述賢

淡江大學/管理學院/管理科學研究所碩士班/碩士(2010年)

https://doi.org/10.6846/TKU.2010.00323

摘要

過去二十年來，企業皆以利用多通路的策略來行銷，多通路的策略可增加企業的範圍，並擴大與消費者的接觸，達成消費者的多種需求，選擇他們喜好的通路，讓消費者使用企業所安排好的通路組合；亦可增加產品進入市場的機會增加廠商的範圍；其目標是將通路做資源分配，以滿足消費者和利潤極大化。

　　隨著多通路的分配越來越普遍，消費者不斷地面臨購買與產品選擇，且偏好不同的通路。本研究以資訊3C產品為例，採用資料採礦（data mining）分析之相關應用技術，以集群分析與關聯法則探討消費者在購買過程中，哪些因素會造成消費者對通路與產品有所區隔，而不同區隔的消費者，偏好在何種通路型態下購買的產品項目以及品牌名稱。

　　研究結果發現，不同集群的消費者在各自以通路及產品做為選擇因素的區隔前提下，所重視的通路屬性與產品屬性確實各不相同，並具有不同的消費行為，且購買某些特定產品時，會有所偏好的通路型態，以及產品組合、品牌之間的關聯性，均有其顯著的差異。製造商與通路商可藉此了解不同集群與行銷組合方式，使業者能在前期的行銷策略上，推出更吸引顧客的方案及服務。

關鍵字

通路區隔 ； 產品區隔 ； 資料採礦 ； 關聯法則 ； 集群分析

並列摘要

In the last two decades, the firm all use the multichannel strategy makes a product available to the market through two or more channels of distribution. Multichannel strategies allow firms to reach customers in multiple ways, increasing the firms' reach. In addition, multiple channels allow customers to reach businesses by using their preferred channel, and using a mix of channel formats, as a multichannel marketer's objectives are to distribute resources across the channel mix to satisfy customers and maximize profits.

　As multichannel distribution becomes increasingly prevalent, customers face an expanding array of purchase and communication options. This study take 3C product for example, used data mining technology of the Cluster Analysis and Association Rule to look for the reason that customer approach channel and product segmentation, and the different segment’s customer prefer what kind of product, brand in the differ by channel type. Understand the different clusters and marketing mix, release the plan and service to attract customers in the early marketing strategy. The results showed that different clusters of customers placed importance on different channel, product quality and consumer behavior under valued by the segment. Also had preference channel type on purchase of specific products and the correlation between product portfolio and brand has obvious differences.

並列關鍵字

channel segmentation ； product segmentation ； Data mining ； Association Rule ； Cluster Analysis

參考文獻

劉典嚴（民90）。顧客稀有化下的市場區隔對策,品質月刊，P35-38

楊逢杰（民97）。以本體論為基礎的資料採礦方法於飲料產業的產品光譜及品牌光譜之研究。淡江大學管理科學研究所碩士論文。未出版。台北縣。

Agrawal, R., Imielinski, T., & Swami, A. (1993). Mining association rules between sets of items in large databases. ACM SIGMOD Conference, Washington DC, USA, 254-259.

Alba, J., Lynch, J., Weitz, B., Janiszewski, C., Lutz, R., Sawyer, A., & Wood, S. (1997). Interactive home shopping, consumer, retailer and manufacturer incentives to participate in electronic marketplaces. Journal of Marketing, 61 (July), 38-53.

Amaratunga, D., & Cabrera, J. (2004). Mining data to find subsets of high activity. Journal of Statistical Planning and Inference, 122(1), 23-41.