Skip to main content
Open Access Publications from the University of California


UCLA Electronic Theses and Dissertations bannerUCLA

Forecasting and Improving the Call Center Operations - Time Series approach and Queueing theory approach


This paper mainly aims to provide the data story to the call center to improve operations, assisting the Business Experience Team to make data-driven decisions. We intend to capture the pattern of current trends and seasonality, as well as the forecasting for the next peak season call volume by time series approach. More importantly, we would like to identify the optimum staffing levels needed to meet certain service goals by implementing queueing model. In order to predict the baseline and the peak season of the call volume, we compare 2 time series models: ARIMA (autoregressive integrated moving averages) model and Holt-Winters exponential smoothing model. The later one gives a better prediction of the call volume. Moreover, we employ 3 classical models (ErlangC, ErlangB and ErlangA models) to find the relationship between the number of operators needed and the wait time of customers in the queue. We end up with the conclusion that increasing 5 operators could achieve the target: 95% of phone calls are answered within 5 minutes.

Main Content
For improved accessibility of PDF content, download the file to your device.
Current View