Delay Predictors in Multi-skill Call Centers: An Empirical Comparison with Real Data

We examine and compare different delay predictors for multi-skill call centers. Each time a new call (customer) arrives, a predictor takes as input some observable information from the current state of the system, and returns as output a forecast of the waiting time for this call, which is an estimate of the expected waiting time conditional on the current state. Any relevant observable information can be included, e.g., the time of the day, the set of agents at work, the queue size for each call type, the waiting times of the most recent calls who started their service, etc. We consider predictors based on delay history, regularized regression, cubic spline regression, and deep feedforward artificial neural networks. We compare them using real data obtained from a call center. We also examine the issue of how to select the input variables for the predictors.

[1]  Yoshua Bengio,et al.  Deep Sparse Rectifier Neural Networks , 2011, AISTATS.

[2]  C. R. Deboor,et al.  A practical guide to splines , 1978 .

[3]  Ward Whitt,et al.  Predicting Queueing Delays , 1999 .

[4]  R. Tibshirani,et al.  Lasso and Elastic-Net Regularized Generalized Linear Models [R package glmnet version 4.0-2] , 2020 .

[5]  Ward Whitt,et al.  The Impact of Delay Announcements in Many-Server Queues with Abandonment , 2009, Oper. Res..

[6]  Frauke Degenhardt,et al.  Evaluation of variable selection methods for random forests and omics data sets , 2017, Briefings Bioinform..

[7]  Ward Whitt,et al.  Delay predictors for customer service systems with time-varying parameters , 2010, Proceedings of the 2010 Winter Simulation Conference.

[8]  Yoshua Bengio,et al.  Practical Recommendations for Gradient-Based Training of Deep Architectures , 2012, Neural Networks: Tricks of the Trade.

[9]  Jing Dong,et al.  The Impact of Delay Announcements on Hospital Network Coordination and Waiting Times , 2018, Manag. Sci..

[10]  Erica L. Plambeck,et al.  Accurate Emergency Department Wait Time Prediction , 2016, Manuf. Serv. Oper. Manag..

[11]  Ward Whitt,et al.  Real-Time Delay Estimation Based on Delay History , 2009, Manuf. Serv. Oper. Manag..

[12]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[13]  Witold R. Rudnicki,et al.  Feature Selection with the Boruta Package , 2010 .

[14]  Pascal Vincent,et al.  Unsupervised Feature Learning and Deep Learning: A Review and New Perspectives , 2012, ArXiv.

[15]  Yoshua Bengio,et al.  Knowledge Matters: Importance of Prior Information for Optimization , 2013, J. Mach. Learn. Res..

[16]  Trevor Hastie,et al.  Regularization Paths for Generalized Linear Models via Coordinate Descent. , 2010, Journal of statistical software.

[17]  Razvan Pascanu,et al.  Pylearn2: a machine learning research library , 2013, ArXiv.

[18]  Ward Whitt,et al.  Real-Time Delay Estimation in Overloaded Multiserver Queues with Abandonments , 2009, Manag. Sci..

[19]  Pierre L'Ecuyer,et al.  Inter-dependent, heterogeneous, and time-varying service-time distributions in call centers , 2016, Eur. J. Oper. Res..

[20]  Alan Y. Chiang,et al.  Generalized Additive Models: An Introduction With R , 2007, Technometrics.

[21]  Daniela M. Witten,et al.  An Introduction to Statistical Learning: with Applications in R , 2013 .

[22]  Jean G. Vaucher,et al.  SSJ: a framework for stochastic simulation in Java , 2002, Proceedings of the Winter Simulation Conference.

[23]  Pierre L'Ecuyer,et al.  Waiting time predictors for multi-skill call centers , 2015, 2015 Winter Simulation Conference (WSC).

[24]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[25]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[26]  Matthias Weidlich,et al.  Queue mining for delay prediction in multi-class service processes , 2015, Inf. Syst..

[27]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[28]  Pierre L'Ecuyer,et al.  New history-based delay predictors for service systems , 2016, 2016 Winter Simulation Conference (WSC).