Learning to Prioritize IT Tickets: A Comparative Evaluation of Embedding-based Approaches and Fine-Tuned Transformer Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: LÊ, Minh Tri, Ait-Bachir, Ali
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908724580319232
author LÊ, Minh Tri
Ait-Bachir, Ali
author_facet LÊ, Minh Tri
Ait-Bachir, Ali
contents Prioritizing service tickets in IT Service Management (ITSM) is critical for operational efficiency but remains challenging due to noisy textual inputs, subjective writing styles, and pronounced class imbalance. We evaluate two families of approaches for ticket prioritization: embedding-based pipelines that combine dimensionality reduction, clustering, and classical classifiers, and a fine-tuned multilingual transformer that processes both textual and numerical features. Embedding-based methods exhibit limited generalization across a wide range of thirty configurations, with clustering failing to uncover meaningful structures and supervised models highly sensitive to embedding quality. In contrast, the proposed transformer model achieves substantially higher performance, with an average F1-score of 78.5% and weighted Cohen's kappa values of nearly 0.80, indicating strong alignment with true labels. These results highlight the limitations of generic embeddings for ITSM data and demonstrate the effectiveness of domain-adapted transformer architectures for operational ticket prioritization.
format Preprint
id arxiv_https___arxiv_org_abs_2512_17916
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning to Prioritize IT Tickets: A Comparative Evaluation of Embedding-based Approaches and Fine-Tuned Transformer Models
LÊ, Minh Tri
Ait-Bachir, Ali
Computation and Language
Artificial Intelligence
Prioritizing service tickets in IT Service Management (ITSM) is critical for operational efficiency but remains challenging due to noisy textual inputs, subjective writing styles, and pronounced class imbalance. We evaluate two families of approaches for ticket prioritization: embedding-based pipelines that combine dimensionality reduction, clustering, and classical classifiers, and a fine-tuned multilingual transformer that processes both textual and numerical features. Embedding-based methods exhibit limited generalization across a wide range of thirty configurations, with clustering failing to uncover meaningful structures and supervised models highly sensitive to embedding quality. In contrast, the proposed transformer model achieves substantially higher performance, with an average F1-score of 78.5% and weighted Cohen's kappa values of nearly 0.80, indicating strong alignment with true labels. These results highlight the limitations of generic embeddings for ITSM data and demonstrate the effectiveness of domain-adapted transformer architectures for operational ticket prioritization.
title Learning to Prioritize IT Tickets: A Comparative Evaluation of Embedding-based Approaches and Fine-Tuned Transformer Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2512.17916