Improving customer routing in contact centers: An automated triage design based on text analytics

Abstract

We propose an automated triage design for intelligent customer routing in live-chat contact centers and demonstrate its implementation using a realworld data set from an S&P 500 firm. The proposed design emerges as a synthesis of text analytics and predictive machine learning methods. Using numerical experiments based on the simulation of the firm's contact center, we demonstrate the service level, time, and labor cost benefits of the automated design over two other triage designs (i.e., customer choice triage and human expert triage) that are commonly employed in the real world. Through additional analyses, we explore the generalizability of the automated design for creating solutions for different types of communication channels. Our work has implications for managing customer relations under emerging communication technologies (e.g., live-chat, e-mail, and social media) and more broadly for demonstrating the use of text analytics and machine learning to improve Operations Management practice.

An ensemble machine learning approach for forecasting credit risk of agricultural SMEs’ investments in agriculture 4.0 through supply chain finance

“…EML is a group leaning approaches that make use of a set of individuals, independent and complementary ML methods to solve the same problem in order to yield better accuracy with collective intelligence (Ilk et al, 2020 ). The common feature of EML approaches is the reiterated running of the base ML algorithm to a sample retrieved from the training dataset.…”

“…Following each running of the algorithm, a new classifier is created and appended to the ensemble (Webb & Zheng, 2004 ). The classification process is conducted by each classifier of the ensemble in isolation from the other classifiers before the ensuing votes fit together to release a single final classification (Shang & Goes, 2020 ).…”

Editorial:Intervention‐basedresearch (IBR)—What, where, and how to use it in operations management

“…Rather, all three papers described research that began from a failed attempt to apply theory to a problem, resulting in a new understanding of the problem or an expansion of the set of theories used to solve the problem. The department remains receptive to the traditional DS approach (e.g., Ilk et al, 2020). The feedback process that results from confronting a theory with reality has now been shown to produce knowledge that may well meet the requirements for publication in JOM , so we expect to see more papers being published in JOM that use the IBR approach than DS.…”

“…Improving Customer Routing in Contact Centers: An Automated Triage Design based on Text-Analytics (Ilk, Shang, & Goes, 2020) Service delivery Problem: How to match the wide-range service inquiries to the right service agents in a call center to minimize service times and improve service quality? Intervention: Developed a new mechanism to triage customer service calls that was better than existing models used in practice based on existing theories.…”

Exploratory data science for discovery and ex‐ante assessment of operational policies: Insights from vehicle sharing

“…Clearly, the abundance of operational data can be an asset in empirically assessing the impact of such policy changes, improving operations, and strengthening the providers' business models. However, the real‐world evaluation of new operational policy solutions through, for instance, field studies is often risky and possibly infeasible due to the complexity of modern software and operational systems (Ilk, Shang, & Goes, 2020) as well as the associated costs. For smart city service providers, in particular, which are often start‐ups or spin‐offs of established companies, costs may prove prohibitive especially if the potential payoff from new operational policies is largely unclear.…”