Call me maybe : Methods and practical implementation of artificial intelligence in call center arrivals' forecasting

Title data

Albrecht, Tobias ; Rausch, Theresa Maria ; Derra, Nicholas Daniel:
Call me maybe : Methods and practical implementation of artificial intelligence in call center arrivals' forecasting.
In: Journal of Business Research. Vol. 123 (2021) . - pp. 267-278.
ISSN 0148-2963
DOI: https://doi.org/10.1016/j.jbusres.2020.09.033

Project information

Abstract in another language

Machine learning (ML) techniques within the artificial intelligence (AI) paradigm are radically transformingorganizational decision-making and businesses’ interactions with external stakeholders. However, in timeseries forecasting for call center management, there is a substantial gap between the potential and actualuse of AI-driven methods. This study investigates the capabilities of ML models for intra-daily call centerarrivals’ forecasting with respect to prediction accuracy and practicability. We analyze two datasets of anonline retailer’s customer support and complaints queue comprising half-hourly observations over 174.5 weeks.We compare practically relevant ML approaches and the most commonly used time series models via cross-validation with an expanding rolling window. Our findings indicate that the random forest (RF) algorithmyields the best prediction performances. Based on these results, a methodological walk-through example of acomprehensive model selection process based on cross-validation with an expanding rolling window is providedto encourage implementation in individual practical settings

Abstract in another language

Artificial intelligence; Machine learning; Call center forecasting; Predictive analytics