Correo Electrónico
DNINFOA - SIA
Bibliotecas
Convocatorias
Identidad U.N.
Publicado
Modelo de Clasificación de Incidentes Tecnológicos desde un Enfoque de Aprendizaje Automático en Servicios de Seguros
Technological incident classification model from a machine learning approach in insurance services•
DOI:
https://doi.org/10.15446/dyna.v89n221.100070Palabras clave:
clasificación de incidentes; incidentes tecnológicos; seguros; aprendizaje automático (es)classification of incidents; technology incidents; insurance; machine learning (en)
La gestión de incidentes tecnológicos en las compañías de seguros requiere una asignación correcta y oportuna de estos a los equipos de resolución de problemas. La clasificación de tales incidentes por humanos demanda tiempo y conocimiento y, con frecuencia, se ejecuta de manera errónea. Este documento aborda este problema de clasificación desde un enfoque de aprendizaje automático. Se compara el desempeño de cinco métodos de aprendizaje supervisado (regresión logística, árboles de clasificación, bosque aleatorio, análisis lineal discriminante y máquinas de vectores de apoyo) en tres escenarios de inclusión de predictores: estructurado, textos y ambos. El uso de variables no estructuradas mejora considerablemente la precisión de los modelos (ej., Random Forest, muestra de validación: 0,709 con datos estructurados; 0,881 con datos de texto). Además, considerando las implicaciones prácticas de la tasa de clasificación humana correcta (66%) frente a la máquina (88%, Random Forest, SVM o regresión logística), la máquina favorece el ahorro de recursos en la organización. Este artículo es un caso exitoso del aprendizaje automático en la industria de seguros.
Managing technological incidents in insurance companies requires a correct and timely assignment of these to the problem-solving teams. Classifying these incidents by humans demands time and knowledge and is frequently executed erroneously. This paper addresses this classification problem from a machine learning approach. The performance of five supervised learning methods (logistic regression, classification trees, random forest, discriminant linear analysis, support vector machines) is compared in three scenarios of inclusion of predictors: structured, texts, and both. The use of unstructured variables considerably improves the precision of the models (e.g., Random Forest, validation sample: 0.709 using structured data; 0.881 using text data). Moreover, considering the practical implications of the human correct classification rate (66%) vs. machine (88%, Random Forest, SVM, or linear regression), the machine favors resource-saving in the organization. This article is a successful case of machine learning in the insurance industry
Referencias
Al-Hawari, F. and Barhamb, H., A machine learning based help desk system for IT service management, Journal of King Saud University - Computer and Information Sciences, 33(6), pp. 702-718, 2019. DOI: https://doi.org/10.1016/j.jksuci.2019.04.001.
Giurgiu, I., Wiesmann, D., Bogojeska, J., Lanyi, D., Stark, G., Wallace, R., Pereira, M.M and Hidalgo, A.A., On the adoption and impact of predictive analytics for server incident reduction, IBM Journal of Research and Development, 61(1), pp. 9-98, 2017. DOI: https://doi.org/10.1147/JRD.2016.2631400.
Paramesh, S. and Shreedhara, K., Automated IT service desk systems using machine learning techniques, in Data analytics and learning, Singapore, Springer, [online]. 2019, pp. 331-346. Available at: https://link.springer.com/chapter/10.1007/978-981-13-2514-4_28.
Sulaman, S., Weyns, K. and Höst, M., Identification of IT incidents for improved risk analysis by using machine learning, Euromicro Conference on Software Engineering and Advanced Applications, [online]. vol. 41, 2015, pp. 1-5. Available at: https://ieeexplore.ieee.org/document/7302476.
Jan, E., Ayachitula, N., Ni, J. and Zhang, Z., A statistical machine learning approach for ticket mining in IT service delivery, in: 2013 IFIP/IEEE International Symposium on Integrated Network Management (IM 2013), [online]. 2013, pp. 541-546. Available at: https://ieeexplore.ieee.org/document/6573030.
Son, G., Hazlewood, V. and Peterson, G., On automating XSEDE user ticket classification, National Institute for Computational Sciences University of Tennessee, [online]. 14, pp. 1-7, 2014. Available at: https://dl.acm.org/doi/abs/10.1145/2616498.2616549.
Bogojeska, J., Stöckel, D., Zazzi, M. and Kaiser, R., History-alignment models for bias-aware prediction of virological response to HIV combination therapy, Journal of Machine Learning Research, [online]. 22, pp. 118-126, 2012. Available at: https://proceedings.mlr.press/v22/bogojeska12.html.
Maksai, A., Bogojeska, J. and Wiesmann, D., Hierarchical incident ticket classification with minimal supervision, IEEE International Conference on Data Mining, 2014, pp. 923-928. DOI: https://doi.org/10.1109/ICDM.2014.81.
Akbar, M. and Jianglei, H., Vertical domain text classification: towards understanding IT tickets using deep Neural Networks, in The Thirty-Second AAAI Conference on Artificial Intelligence, [online]. 2018. Available at: https://ojs.aaai.org/index.php/AAAI/article/view/11375.
Silva, S., Pereira, R. and Ribeiro, R., Machine learning in incident categorization automation, Iberian Conference on Information Systems and Technologies [CISTI], [online]. vol. 13, 2018. Available at: https://ieeexplore.ieee.org/document/8399244.
Altintas, M. and Cuneyd, A., Machine learning based ticket classification in issue tracking systems, [online]. 2014. Available at: https://docplayer.net/1775410-Machine-learning-based-ticket-classification-in-issue-tracking-systems.html.
Kallis, R., Di Sorbo, A., Canfora, G. and Panichella, S., Ticket tagger machine learning driven, International Conference on Software Maintenance and Evolution [ICSME], [online]. pp. 1-4, 2019. Available at: https://ieeexplore.ieee.org/document/8918993.
Gore, R., Daillo, S., Padilla, J. and Ezell, B., Assessing cyber-incidents using machine learning, International Journal of Information and Computer Security [IJICS], 10(4), pp. 341-360, 2018. DOI: https://doi.org/10.5555/3292793.3292795
Li, H. and Zhan, Z., Machine learning methodology for enhacing automated process in IT incident management, in: Symposium on Network Computing and Applications, [online]. 2012. Available at: https://ieeexplore.ieee.org/document/6299094.
https://cran.r-project.org/, https://cran.r-project.org/, 9 10 2021. [Online]. Available at: https://cran.r-project.org/web/packages/caret/caret.pdf.
cran.r-project.org, Package ‘caret’, 9 10 2021. [Online]. Available at: https://cran.r-project.org/web/packages/caret/caret.pdf.
Diao, Y., Jamjoom, H. and Loewenstern, D., Rule-based problem classification in IT service management, in: 2009 IEEE International Conference on Cloud Computing, New York, 2009. DOI: https://doi.org/10.1109/CLOUD.2009.80.
Cómo citar
IEEE
ACM
ACS
APA
ABNT
Chicago
Harvard
MLA
Turabian
Vancouver
Descargar cita
Licencia
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-SinDerivadas 4.0.
El autor o autores de un artículo aceptado para publicación en cualquiera de las revistas editadas por la facultad de Minas cederán la totalidad de los derechos patrimoniales a la Universidad Nacional de Colombia de manera gratuita, dentro de los cuáles se incluyen: el derecho a editar, publicar, reproducir y distribuir tanto en medios impresos como digitales, además de incluir en artículo en índices internacionales y/o bases de datos, de igual manera, se faculta a la editorial para utilizar las imágenes, tablas y/o cualquier material gráfico presentado en el artículo para el diseño de carátulas o posters de la misma revista.
