信用卡行銷資料庫之顧客遷徙路徑分析

Abstract

企業在消費者行為變動更快速且複雜的環境中，要如何維持與顧客的關係以及了解其需求是十分迫切的，企業在顧客的行銷資源投入與關鍵顧客的抉擇，決定了企業獲利以及經營的成效。資料庫行銷對於落實關係行銷是不可或缺的，廠商透過資料庫的分析得以衡量個別顧客之價值。 本研究認為廠商應從動態的角度觀察顧客價值的增減，事前判別顧客價值的遷移路徑，方能達到開發顧客價值潛力以及預防顧客價值流失。本研究以馬可夫鏈模型為基礎，搭配層級貝氏Probit 模型，推估出顧客在每期刷卡狀態的轉換機率，並設定不同價值狀態遷移路徑，結合人口統計變數，進而預測顧客的價值遷移路徑，本研究以國內某銀行之信用卡資料庫進行實證，並且利用本研究之計算方式與其他計算方式進行預測力比較，據此採取適當的顧客關係行銷之策略。

How does enterprises maintain relationships between customers and to fully understand what the customers really want becomes quite urgent. The investment in marketing resources and the list of key customers determine the profits of enterprises and the results of the management. Database Marketing is a requisite and efficient weapon for firms to put relationship marketing in practice. The task of this practice is to evaluate individual customer value through proper analyses of customers' purchase data. What enterprises need to do is to be able to capture the migration patterns of a customer's value in advance, in order to explore potential customers and prevent inactive customers. Markov chain model and hierarchical Bayesian Probit approach are applied to construct individual customer's purchasing transition probabilities in every state. With the transition matrix and defined customer migration pathways, we can calculate customer correspondence. With the information, the enterprises can indicate key customers and allocate marketing resources more efficiently.