顧客價值發現之研究－ 整合資料探勘技術與顧客終身價值分析

Abstract

顧客關係管理已經成為企業在經營上的重要策略，為了能夠掌握具有價值的顧客，使企業的獲利能夠穩定且成長，顧客的潛在價值發現、維持與增強在現今競爭的商業環境中扮演著企業重要的獲利關鍵成功要素；然而，資料庫中的顧客特質、購買行為樣式等行銷觀點知識是未被觸及以及大量被隱藏的，因此如何進一步從資料庫中來發掘出顧客的潛在價值之特徵及潛在購買行為樣式是值得研究的。在探討過去的文獻後發現，顧客終身價值可以去計算出顧客對於企業貢獻程度，資料探勘可以發掘出顧客的潛在購買行為樣式，兩者間具有相輔相成之效。本研究結合顧客終身價價值分析以及資料探勘的技術來建立出一套模式來找出每位顧客的潛在價值及特徵，透過顧客終身價值分析找出現有價值，以及每位顧客之預期購買金額以及活動機率，藉以計算出其潛在價值。針對現有價值以及潛在價值為基礎來做集群分析。資料探勘方面則以集群結果為基礎來做關聯分析、OLAP以及決策樹，瞭解現有價值以及潛在價值最高的群組之特徵及購買行為樣式，並做為新進顧客的類別之預測與瞭解。最後，本研究點出各集群背後的行銷意涵，提供給管理者在應用顧客關係管理時的參考。

Customer relationship management (CRM) has become an important strategy for businesses. In an environment of intense competition, the finding, maintenance and strengthening of customer value is key to a business in making a profit. Past studies have found that customer lifetime value (CLV) can be used to calculate each customer's contribution to the company, and that data mining can be used to extract customers' potential behavioral patterns and characteristics. Though both are complementary, rarely are there studies applying the two methods at the same time. This research has developed a conceptual framework and process that integrates CLV analysis and data mining technique. It uses CLV analysis to calculate customer current value (CCV) and estimate customer potential value (CPV). Next, based on CCV and CPV, clustering techniques were applied for customer groupings. Finally, a data mining method will be applied to discovering the characteristics and the potential purchasing behavioral pattern of the most valuable customer group. By establishing a customer value pyramid combing the marketing implications of each cluster and suggestions, this research served as a reference for managers engaging in CRM.