大型呼叫中心人工呼入量的最小二乘支持向量机模型-控制理论与应用.PDF

26 7 Vol. 26 No. 7 2009 7 Control Theory Applications Jul. 2009 :2009 , (1. , 100876; 2. , 100032) : , , (LS-SVM), . , , . , LS-SVM. : ; ; : TP181 : A Large call-centers’ arrival-rates prediction models based on the least squares support vector machine LI Da-chuan , XIN Zhan-hong (1. School of Economics and Management, Beijing University of Posts and Telecommunications, Beijing 100876, China; 2. China Mobile Communications Corporation, Beijing 100032, China) Abstract: In analyzing the data from a large call center, we find that arrival rates can be split into the daily-arrival-rate and the time-period-arrival-rate. Based on the least squares support vector machine theory(LS-SVM), predicting models of the daily-arrival-rate and the time-period-arrival-rate are established. Simulation experiments show that these models are good at regression and forecasting. Compared with Back-Propagation(BP) neural network prediction models, these models give better prediction results. Key words: call center; forecasting; least squares support vector machine theory(LS-SVM) 1 (Introduction) , . . , , , . , . , , , . . , 2 (Call center’s arrival , . (support vector machine) rates prediction)