Bibliographic citations
Chotón, C., Laos, J., Cacho, L. (2024). Propuesta de un modelo de asignación automatizada de tickets para la reducción de plazos de atención de incidentes del Service Desk de una financiera usando aprendizaje supervisado [Trabajo de investigación, Universidad Peruana de Ciencias Aplicadas (UPC)]. http://hdl.handle.net/10757/682911
Chotón, C., Laos, J., Cacho, L. Propuesta de un modelo de asignación automatizada de tickets para la reducción de plazos de atención de incidentes del Service Desk de una financiera usando aprendizaje supervisado [Trabajo de investigación]. PE: Universidad Peruana de Ciencias Aplicadas (UPC); 2024. http://hdl.handle.net/10757/682911
@mastersthesis{renati/1032600,
title = "Propuesta de un modelo de asignación automatizada de tickets para la reducción de plazos de atención de incidentes del Service Desk de una financiera usando aprendizaje supervisado",
author = "Cacho Aniceto, Luz Stefany",
publisher = "Universidad Peruana de Ciencias Aplicadas (UPC)",
year = "2024"
}
The purpose of this research project is to develop and propose a model based on supervised learning to automate the ticket assignment process at the service desk of a financial institution. The current problem lies in the significant delays during the assignment of requests and incidents to the resolution groups (specialists), which has generated high levels of dissatisfaction among users, leading to an increase in complaints and possible administrative sanctions for the company. Likewise, the lack of a clear understanding of the functions of the resolution groups and the high turnover of analysts at the service desk have intensified this situation. During the research phase, an exhaustive analysis of various algorithms and Machine Learning solutions applied to ticket management was carried out, identifying the main challenges and obstacles that limit their effective implementation in organizations. Consequently, the proposed model is aimed at optimizing the automatic assignment of IT resolution groups in charge of supporting the institution's applications and services, with the purpose of improving efficiency and reducing response times. For the implementation of the model, a series of methodological stages were defined, which are detailed in the following sections. Once these stages were completed, the results obtained confirmed that the implementation of the automated assignment algorithm based on supervised learning techniques allowed the assignment time of the resolution groups to be reduced by 82.6%. In addition, a 22.2% improvement was seen in the resolution of incidents within the times agreed in the SLA (Service Level Agreement) established by the financial institution. This study highlights the potential of Machine Learning technologies to transform and optimize critical processes in the management of IT services, providing solutions that not only increase user satisfaction, but also improve the internal operability of organizations.
This item is licensed under a Creative Commons License