Optimal call center forecasting and staffing

Sihan Ding; Ger Koole

doi:10.1017/S0269964820000595

Optimal call center forecasting and staffing

Sihan Ding^*, Ger Koole

^*Corresponding author for this work

Mathematics

Research output: Contribution to Journal › Article › Academic › peer-review

262 Downloads (Pure)

Abstract

In this paper, we consider a two-stage call center staffing model. In the first stage, the interval staffing levels are set under arrival rate uncertainty. In the second stage, these initial staffing levels are corrected to the right value based on more precise arrival rate information. We show that this problem is of newsvendor type, where the costs are the initial staffing costs plus the second stage adaptation costs. We show that we should initially staff according to a quantile of the distributional forecast, rather than the mean. It is also shown that the errors in staffing are approximately linear in the forecasting errors. This leads to the conclusion that the weighted sum of errors should be the error measurement in call center forecasting, since minimizing, it minimizes the total staffing costs. In special cases where the costs are symmetric for over-and understaffing, this is equivalent to minimizing the weighted absolute percentage error.

Original language	English
Pages (from-to)	254-263
Number of pages	10
Journal	Probability in the Engineering and Informational Sciences
Volume	36
Issue number	2
Early online date	16 Feb 2022
DOIs	https://doi.org/10.1017/S0269964820000595
Publication status	Published - Apr 2022

Bibliographical note

Funding Information:
The authors are grateful to Bert Zwart and Rob van der Mei, to the anonymous referees for their useful comments, and to Giuseppe Catanese for supplying us with the data of . This project was executed while the first author was at CWI Amsterdam and was partially funded by the Dutch Defense Department and an NWO STAR grant.

Publisher Copyright:
Copyright © The Author(s), 2022. Published by Cambridge University Press.

Funding

The authors are grateful to Bert Zwart and Rob van der Mei, to the anonymous referees for their useful comments, and to Giuseppe Catanese for supplying us with the data of . This project was executed while the first author was at CWI Amsterdam and was partially funded by the Dutch Defense Department and an NWO STAR grant.

Keywords

applied probability
call centers
error measurements
forecasting
staffing

Access to Document

10.1017/S0269964820000595

optimal-call-center-forecasting-and-staffingFinal published version, 327 KBLicence: Article 25fa Dutch Copyright Act

Persistent URL (handle)

Persistent link

Cite this

@article{5e7e650af2084b3f81c1b7fcc6097e5f,

title = "Optimal call center forecasting and staffing",

abstract = "In this paper, we consider a two-stage call center staffing model. In the first stage, the interval staffing levels are set under arrival rate uncertainty. In the second stage, these initial staffing levels are corrected to the right value based on more precise arrival rate information. We show that this problem is of newsvendor type, where the costs are the initial staffing costs plus the second stage adaptation costs. We show that we should initially staff according to a quantile of the distributional forecast, rather than the mean. It is also shown that the errors in staffing are approximately linear in the forecasting errors. This leads to the conclusion that the weighted sum of errors should be the error measurement in call center forecasting, since minimizing, it minimizes the total staffing costs. In special cases where the costs are symmetric for over-and understaffing, this is equivalent to minimizing the weighted absolute percentage error.",

keywords = "applied probability, call centers, error measurements, forecasting, staffing",

author = "Sihan Ding and Ger Koole",

note = "Funding Information: The authors are grateful to Bert Zwart and Rob van der Mei, to the anonymous referees for their useful comments, and to Giuseppe Catanese for supplying us with the data of . This project was executed while the first author was at CWI Amsterdam and was partially funded by the Dutch Defense Department and an NWO STAR grant. Publisher Copyright: Copyright {\textcopyright} The Author(s), 2022. Published by Cambridge University Press.",

year = "2022",

month = apr,

doi = "10.1017/S0269964820000595",

language = "English",

volume = "36",

pages = "254--263",

journal = "Probability in the Engineering and Informational Sciences",

issn = "0269-9648",

publisher = "Cambridge University Press",

number = "2",

}

TY - JOUR

T1 - Optimal call center forecasting and staffing

AU - Ding, Sihan

AU - Koole, Ger

N1 - Funding Information: The authors are grateful to Bert Zwart and Rob van der Mei, to the anonymous referees for their useful comments, and to Giuseppe Catanese for supplying us with the data of . This project was executed while the first author was at CWI Amsterdam and was partially funded by the Dutch Defense Department and an NWO STAR grant. Publisher Copyright: Copyright © The Author(s), 2022. Published by Cambridge University Press.

PY - 2022/4

Y1 - 2022/4

N2 - In this paper, we consider a two-stage call center staffing model. In the first stage, the interval staffing levels are set under arrival rate uncertainty. In the second stage, these initial staffing levels are corrected to the right value based on more precise arrival rate information. We show that this problem is of newsvendor type, where the costs are the initial staffing costs plus the second stage adaptation costs. We show that we should initially staff according to a quantile of the distributional forecast, rather than the mean. It is also shown that the errors in staffing are approximately linear in the forecasting errors. This leads to the conclusion that the weighted sum of errors should be the error measurement in call center forecasting, since minimizing, it minimizes the total staffing costs. In special cases where the costs are symmetric for over-and understaffing, this is equivalent to minimizing the weighted absolute percentage error.

AB - In this paper, we consider a two-stage call center staffing model. In the first stage, the interval staffing levels are set under arrival rate uncertainty. In the second stage, these initial staffing levels are corrected to the right value based on more precise arrival rate information. We show that this problem is of newsvendor type, where the costs are the initial staffing costs plus the second stage adaptation costs. We show that we should initially staff according to a quantile of the distributional forecast, rather than the mean. It is also shown that the errors in staffing are approximately linear in the forecasting errors. This leads to the conclusion that the weighted sum of errors should be the error measurement in call center forecasting, since minimizing, it minimizes the total staffing costs. In special cases where the costs are symmetric for over-and understaffing, this is equivalent to minimizing the weighted absolute percentage error.

KW - applied probability

KW - call centers

KW - error measurements

KW - forecasting

KW - staffing

UR - http://www.scopus.com/inward/record.url?scp=85124962505&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85124962505&partnerID=8YFLogxK

U2 - 10.1017/S0269964820000595

DO - 10.1017/S0269964820000595

M3 - Article

AN - SCOPUS:85124962505

SN - 0269-9648

VL - 36

SP - 254

EP - 263

JO - Probability in the Engineering and Informational Sciences

JF - Probability in the Engineering and Informational Sciences

IS - 2

ER -

Optimal call center forecasting and staffing

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Persistent URL (handle)

Other files and links

Fingerprint

Cite this