Forecasting Call Center Arrivals Using Multilayer Perceptron Combined with Time Lags

Creative Commons License

Ballouch M., Akay M. F., Erdem S., Tartuk M., Nurdağ T. F.

5th International Mediterranean Science and Engineering Congress, Adana, Turkey, 21 - 23 October 2020, pp.1-5

  • Publication Type: Conference Paper / Full Text
  • City: Adana
  • Country: Turkey
  • Page Numbers: pp.1-5
  • Çukurova University Affiliated: Yes

Abstract

A call center is an office equipped to handle a large volume of telephone calls for an organization, for which the ability to forecast calls is a key factor. By forecasting the number of calls accurately, a company can plan staffing needs, meet service level requirements, improve customer satisfaction and benefit from many other optimizations. In this paper, we develop Multilayer Perceptron (MLP) based models combined with time lags to forecast the number of call arrivals in a call center. We forecast 12, 24, 36 and 48 values ahead and the performance of the forecasting models has been evaluated using the Mean Absolute Error (MAE). The results show that the MAE values change between 1.50 and 13.58.