Departmental News - Computer Science and Software Engineering - University of Canterbury - New Zealand

Seminar: Forecasting Intraday Arrivals at a Call Centre: A Neural Network and Functional Outlier Mod


2015-12-14

Abstract

Forecasts of call arrivals at a call centre are required for short term operational decisions regarding resource deployment such as the scheduling of staff, as well as medium to long-term decisions about resource allocation including the hiring and training of staff. A key challenge for call centres remains the forecasting of high frequency call arrivals, collected in hourly or shorter time buckets. In addition to the complex intraday, intraweek and inter-year seasonal cycles, call arrival data typically contain a large number of anomalous days, driven by the occurrence of holidays, special events, promotional activities and system failures. This study evaluates the use of a variety of forecasting methods for forecasting intraday call arrivals in the presence of such outliers.

Apart from established statistical methods we consider artificial neural networks (ANNs). Based on the modelling flexibility of the latter we introduce and evaluate different methods to encode the outlying periods. Using intraday arrival series from a call centre operated by one of Europe’s leading entertainment companies, we provide new insights on the impact of outliers on the performance of established forecasting methods, particularly considering the complexity of each method. Results show that ANNs forecast call centre data accurately, and are capable of modelling complex outliers using relatively simple outlier modelling approaches. We argue that the relative complexity of ANNs over standard statistical models is offset by the simplicity of coding multiple and unknown effects during outlying periods with ease.

Bio

Dr. Devon K. Barrow is a Senior Lecturer at Coventry Business School. He was previously a Research Associate at the Lancaster Centre for Forecasting and at present holds a Visiting Researcher position within the Centre. His research focuses on time series prediction with neural networks and statistical methods, with a particular emphasis on forecast combination and model selection. He also has an interest in education and pedagogical design with specific application to the forecasting domain. Dr. Barrow has worked on real world problems in call centre, electric load, and utility forecasting and provided knowledge transfer and consultancy in forecasting and supply chain management within the Manufacturing and Retail Sectors. He has delivered academic and practitioner training courses in forecasting, and presents regularly at leading international forecasting conferences. He is a past member of the Association of Certified Chartered Accountants (ACCA) and a member of the Chartered Institute of Logistics and Transport (CILT).

Acknowledgements

This research visit is funded through the support of the Coventry University Pump-prime Grant Scheme.

 

  • Phone: +64 3 364 2362
    Fax: +64 3 364 2569
    admin@cosc.canterbury.ac.nz
  • Computer Science and Software Engineering
    University of Canterbury
    Private Bag 4800, Christchurch
    New Zealand
  • Follow us
    FacebookYoutubetwitterLinked In