FORECASTING CUSTOMER SUPPORT RESOLUTION TIMES THROUGH AUTOMATED MACHINE LEARNING

Anton A. Gerunov ()
Additional contact information
Anton A. Gerunov: Faculty of Economics and Business Administration, Sofia University “St. Kliment Ohridski”, Sofia

Economics and Management, 2022, vol. 19, issue 2, 1-11

Abstract: This article focuses on modeling and forecasting the resolution time of customer support tickets. To this end we leverage data from a process aware information system and compare manual training of several state-of-the-art benchmark models (neural network, regression, k-Nearest neighbors, random forest, and support vector machine) to automated model training using the H2O framework. The best performer among the automated machine learning models has much higher forecast accuracy than the benchmark models. This indicates that automated machine learning is a feasible way to approach process modeling problems and may be fruitfully utilized to forecast relevant process metrics.

Keywords: customer support; resolution time; business process mining; prediction; automated machine learning; AutoML; H2O framework (search for similar items in EconPapers)
JEL-codes: C44 C45 C53 (search for similar items in EconPapers)
Date: 2022
References: Add references at CitEc
Citations:

Downloads: (external link)
https://em.swu.bg/images/SpisanieIkonomikaupload/S ... _AutoML_20221129.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:neo:journl:v:19:y:2022:i:2:p:1-11

DOI: 10.37708/em.swu.v19i2.1

Access Statistics for this article

More articles in Economics and Management from Faculty of Economics, SOUTH-WEST UNIVERSITY "NEOFIT RILSKI", BLAGOEVGRAD Contact information at EDIRC.
Bibliographic data for series maintained by Vladislav Krastev ().