| 摘要: | 隨著資訊科技及網際網路之快速發展，企業生存所面臨的壓力有別於過往，在市場的高度競爭下，企業唯有瞭解及掌握顧客才是致勝關鍵，管理大師彼得．杜拉克（Peter Drucker）早於1945年指出「企業的存在取決於顧客，顧客才是企業的基礎」。對企業而言，若能將有限的資源用來強化在80/20法則中的目標顧客群上，同時了解有相似特徵的顧客群，其消費的行為模式，進而提供適切所需的商品組合提昇顧客滿意度，且銷售後是對企業有最大利潤的，才能使企業的行銷資源發揮最大的效益。
本研究將以零售業交易資料庫為對象，應用Hughes(1994) 所提出的RFM Model作一修改，將其中的M(購買金額)改為P(銷售利潤)、Kohonen(1982)提出的自組織映射神經網路(SOM)、資料探勘(Data Mining)中關聯規則(Association rules)等技術進行實証分析。由於利潤為銷售價格、銷售數量等因素交互作用之結果，任何一個因素的改變皆會使利潤變動，所以在上述的關聯規則中，會將顧客所購買數量因素，切割轉換為對應字母後加入關聯規則演算法中來進行挖掘，以求得真正符合現實效益之加權關聯規則，再將商品進行Top-N的推薦，作為顧客選購的參考。最後，根據實驗顯示，本研究除達到對主要的”最佳型忠誠顧客”群別提供差異化行銷的目的外，也讓企業獲得較高的利潤。
In the era of great competition, the way in which companies interact with their cus-tomers have changed dramatically over the past few years. A customer's continuing business is no longer guaranteed. As a result, companies have found that they need to understand their target customers better and to quickly respond to their wants and needs. Value in companies’ mind constituted only one thing - how much the customer is will-ing to pay for the product. "What is our business is not determined by the producer but by the consumer," wrote Drucker in 1954.
Few rules are more widely quoted in marketing today than the 80/20 Rule, which states that 80% of your sales come from just 20% of your customer base. In this age of relationship marketing, this rule has become an often-heard battle cry to focus our ef-forts on maintaining the loyalty of customers belonging to the golden 20% that drive most of our business, while spending less effort on the trivial other 80%. Thus, it is very important to identify the customer(s) for your product or service and determine what they consider important; and examine how an organization determines requirements, expectations and preferences of customers and markets, and how the organization builds relationships with customers and determines the key factors that lead to customer acqui-sition, satisfaction, retention and to business expansion.
This study will modify the RFM Model (Hughes, 1994) for developing a conceptual frame work to analyze the customer preferences and behaviors in a retailer market. In addition, this study will find out the association rules with SOM(Kohonen,1982) and data mining for understanding the consuming behavior and profit contribution. As we know that the price and sales volume that impact directly upon sales revenues and prof-itability. What the customers really wants provides a business and technological over-view of data mining and outlines how, along with sound business processes and com-plementary technologies, data mining can reinforce and redefine customer relationships. From this experiment, we can find out who are our best and / or most loyal customers. Furthermore, it can help a company objectively identify, profile, model, select, promote and track "Loyal" and "Best" customers. |
