Forecasting Call Center Arrivals Using XGBoost Combined with Consecutive and Periodic Lookback

Abstract

For companies operating in the call center service sector, it is essential to plan and manage call center employees regularly and optimize the costs. Therefore, agent planning needs to be performed in an optimum way in the call center sector. To make customer representative planning, information on the number of incoming calls is needed to forecast call counts. This study aims to forecast the number of calls using the Extreme Gradian Boosting (XGBoost) combined with consecutive and periodic lookback to be able to plan the number of representatives at specified intervals per operation in the call center sector. Models based on Moving Average (MA) have also been developed for comparison purposes. Mean Absolute Error (MAE) has been used to evaluate the performance of forecast models whereas the generalization errors of the models were evaluated using 80/20 split for training and testing. Forecasts were generated in daily format for four different weeks. The results show that XGBoost performs better than MA for all four different weeks and produces predictions within limits of acceptable accuracy.

Keywords

• Machine learning
• Regression
• Forecasting
• Call center

References

1. ALBRECHT, T., RAUSCH, T. M., & DERRA, N. D. (2021). Call me maybe: Methods and practical implementation of artificial intelligence in call center arrivals’ forecasting. Journal of Business Research, 123, 267-278.
2. BALLOUCH, M., AKAY, M.F., ERDEM, S., TARTUK, M., NURDAG T.F., YURDAGUL, H.H., “Forecasting Call Center Arrivals Using Machine Learning,” Osmaniye Korkut Ata University Journal of Natural and Applied Sciences, vol. 4, no. 1, pp. 96-101, 2021.
3. BARROW, D., & KOURENTZE, N. (2018). The impact of special days in call arrivals forecasting: A neural network approach to modelling special days. European Journal of Operational Research, 264(3), 967-977.
4. CAO, B., WU, J., CAO, L., XU, Y., & FAN, J. (2020). Long-term and multi-step ahead call traffic forecasting with temporal features mining. Mobile Networks and Applications, 25(2), 701-712.
5. CAO, L., MA, K., CAO, B., & FAN, J. (2019, August). Forecasting long-term call traffic based on seasonal dependencies. In International Conference on Collaborative Computing: Networking, Applications and Worksharing (pp. 231-246). Springer, Cham.
6. JALAL, M. E., HOSSEINI, M., & KARLSSON, S. (2016). Forecasting incoming call volumes in call centers with recurrent neural networks. Journal of Business Research, 69(11), 4811-4814.
7. KANTHANATHAN, C., CARTY, G., RAJA, M. A., & RYAN, C. (2020, December). Recurrent Neural Network based Automated Workload Forecasting in a Contact Center. In 2020 3rd International Conference on Intelligent Sustainable Systems (ICISS) (pp. 1423-1428). IEEE.
8. KIM, T., KENKEL, P., & BRORSEN, B. W., Forecasting hourly peak call volume for a rural electric cooperative call center. Journal of Forecasting 2012; 31(4), 314-329.

9. LESZKO, D. (2020). Time series forecasting for a call center in a Warsaw holding company (Doctoral dissertation). LI, J. (2018). Forecasting and Improving the Call Center Operations-Time Series Approach and Queueing Theory Approach (Doctoral dissertation, UCLA).
10. MOAZENİ, S., and ANDRADE, R., “A Data-Driven Approach to Predict an Individual Customer’s Call Arrival in Multichannel Customer Support Centers,” 2018 IEEE International Congress on Big Data (BigData Congress), San Francisco, CA, 2018, pp. 66-73.
11. MOTTA, G., BARROERO, T., SACCO, D., & YUO, L. (2013, May). Forecasting in multi-skill call centers: a multi-agent multi-service (MAMS) approach: research in progress. In 2013 Fifth International Conference on Service Science and Innovation (pp. 223-229). IEEE.
12. RAFIQ, M., (2017). Using Personalized Model to Predict Traffic Jam in Inbound Call Center. ICST Transactions on Scalable Information Systems. 4. 152101. 10.4108/eai.18-1-2017.152101.
13. ZHANG, M., SHENG, Y., TIAN, N., LIU, W., WANG, H., ZHU, L., & XU, Q. (2021, April). Research and Application of Traffic Forecasting in Customer Service Center Based on ARIMA Model and LSTM Neural Network Model. In Journal of Physics: Conference Series (Vol. 1881, No. 3, p. 032063). IOP Publishing.