改进的K-Means算法在信用卡客户细分中的应用

The application of an improved K-Means algorithm in credit card customer segmentation

典型的K-Means算法适用于进行客户细分,但是该算法要求用户必须事先给出精确的k值,这在一定程度上影响和限制了其应用.通过使用聚类有效性函数对其进行改进,克服了该算法要求用户必须事先给定k值的缺点,并采用改进的K-Means算法对信用卡客户进行细分,建立了基于消费行为的客户细分模型.实验结果表明,从该客户细分模型可获知信用卡客户的消费行为模式,为其提供个性化服务.

The K-Means algorithm aims to minimize the sum of squared distances between all points and the cluster center,and it requires the number of clusters to be known beforehand Which limits its application to some extent.A new method is based on the K-Means algorithm,which overcomes the limitation of having to indicate the number of cluster by using validation function.And it is applied to construct a customer segmentation model based on consumer behavior.Experimental results show that we can get characteristics of consumer behavior patterns from the model in order to provide the differentiated service for the credit card customers.