Decision Trees for Helpdesk Advisor Graphs

TL;DR

This paper presents a decision tree-based approach to create a helpdesk advisor network that improves support quality and guides less experienced staff through complex troubleshooting in telecommunications.

Contribution

It introduces a novel decision tree framework for modeling support staff and facilitating on-the-job training for helpdesk agents.

Findings

Models identify effective advisors based on performance metrics.

The approach enhances decision support for less experienced staff.

Supports deployment of dormant tutors for improved troubleshooting.

Abstract

We use decision trees to build a helpdesk agent reference network to facilitate the on-the-job advising of junior or less experienced staff on how to better address telecommunication customer fault reports. Such reports generate field measurements and remote measurements which, when coupled with location data and client attributes, and fused with organization-level statistics, can produce models of how support should be provided. Beyond decision support, these models can help identify staff who can act as advisors, based on the quality, consistency and predictability of dealing with complex troubleshooting reports. Advisor staff models are then used to guide less experienced staff in their decision making; thus, we advocate the deployment of a simple mechanism which exploits the availability of staff with a sound track record at the helpdesk to act as dormant tutors.