One-Step Dynamic Classifier Ensemble Model for Customer Value Segmentation with Missing Values

Table 1

Attribute description of “China churn” dataset.

Attribute	Name	Missing; rate (%)
	Total consumption times	7.37
	Total consumption amount	6.76
	Total cash times	4.95
	Customer survival time	8.63
	Total contributions	11.12
	Valid survival time	8.05
	Average amount ratio	10.75
	Whether associated charge	12.18
	Consumption times in the last 1 month	2.09
	Consumption times in the last 2 months	3.13
	Consumption times in the last 3 months	8.08
	Consumption times in the last 4 months	9.31
	Consumption times in the last 5 months	3.87
	Cash times in the last 1 month	5.07
	Cash times in the last 2 months	7.04
	Cash times in the last 3 months	8.97
	Cash times in the last 6 months	10.60
	Months of transaction times reducing continuously	8.48
	If overdue in the last 1 month	7.80
	If overdue in the last 2 months	13.76
	Amount usage ratio in the last 1 month/historical average usage ratio	6.11
	Sex	2.70
	Annual income	14.84
	Nature of work industry	11.18
	Education	8.63