Mining for Action-Rules in Large Decision Tables Classifying Customers
Mining for Action-Rules in Large Decision Tables Classifying Customers
复制标题
挖掘大型决策表中的行动规则对客户进行分类
DOI：
10.1007/978-3-7908-1846-8_6
复制
发表时间：
2000
期刊：
影响因子：
--
通讯作者：
Alicja Wieczorkowska
中科院分区：
文献类型：
--
作者：
Z. Ras;Alicja Wieczorkowska
将客户分为不同盈利能力组的大型决策表用于挖掘对客户进行分类的规则。属性分为两组：稳定和灵活。所谓稳定属性，我们指的是银行无法改变其价值的属性（例如年龄、婚姻状况、子女数量）。另一方面，价值可以被银行改变或影响的属性（如百分比利率或在某个地区购买房屋的贷款批准）被称为弹性。规则从给定灵活属性的决策表中提取。这类新的规则形成了一个特殊的规则存储库，从中可以构造称为动作规则的新规则。他们表明应该采取什么行动来提高客户的盈利能力。
Large decision tables classing customers into groups of different profitability are used for mining rules classing customers. Attributes are divided into two groups: stable and flexible. By stable attributes we mean attributes which values can not be changed by a bank (age, marital status, number of children are the examples). On the other hand attributes (like percentage rate or loan approval to buy a house in certain area) which values can be changed or influenced by a bank are called flexible. Rules are extracted from a decision table given preference to flexible attributes. This new class of rules forms a special repository of rules from which new rules called action-rules are constructed. They show what actions should be taken to improve the profitability of customers.