Publication:
Exploración de Modelos para Determinar el Incurrido en Seguros de Autos

Thumbnail Image
Files

Files

Primary Posada Aguilar, Camilo Esteban-2022.pdf (1.04 MB)
 Autorizacion.pdf (131.07 KB)
View Statistics
Reference Managers
Mendeley
Indexers
Google Scholar CORE
QR Code
QR Code
Authors

Authors

Posada Aguilar, Camilo Esteban
Abstract (Spanish)
En los seguros generales es particularmente complicado hallar la forma de pronosticar el incurrido del ramo de autos en los amparos de pérdida y hurto parcial. Pronosticar esta cifra es vital para la compañía puesto que se lograría entender el comportamiento del negocio a través de las reservas, la siniestralidad, el índice combinado y la tarifación en caso de que el portafolio sea muy pequeño para realizar un GLM. El propósito de este trabajo es proveer una metodología para pronosticar el incurrido, de tal forma que la reserva de siniestros avisados esté mucho más alineada con el valor de las autopartes en el mercado. Para ello se propone entrenar algoritmos de series de tiempo cuyo output sea un índice de precios de las piezas creado a partir del portafolio de la compañía y su input sean índices económicos y de desempeño del país.
Abstract (English)
In Property and Casualty Insurance is particularly tough to find a way to forecast the reported losses from the car’s insurance coverages of partial and thief loss. Forecast this figure is key for the company, because the business understanding will increase through the reserves, loss ratio, combined ratio and the pricing component if the company has a small portfolio to perform a GLM. The main purpose of the work is provide a methodology for forecasting the reported losses, in such a way that the case reserve will be in line with the auto part’s market. These algorithms were trained from time series whose output is a price index from cars part’s market created through the company’s portfolio and whose outputs would be economic and country’s performance indexes.
Director

Advisors/Directors

Lozano Murcia, Catalina
Extent
76 páginas
URI: https://repositorio.escuelaing.edu.co/handle/001/2085
Collections

Collections

JB - Trabajos de Grado Maestría en Ciencias Actuariales
References

Asteriou, D., & Stephen, H. (2011). Applied Econometrics. New York: Palgrave MacMillan. Awad, M., & Khanna, R. (2015). Efficient Learning Machines. New York: Springer. Banco de la República. (Marzo de 2022). Banco de la República. Obtenido de https://www.banrep.gov.co/es/estadisticas/indice-precios-consumidor-ipc Bernico, M. (2018). Deep Learning Quick Reference. Mumbai: Packt Publishing. Brockwell, P., & Davis, R. (2002). Introduction to Time Series and Forecasting. Nueva York: Springer. Brockwell, P., & Richard, D. (2006). Time Series: Theory and Methods. New York: Springer. Buteikis, A. (2020). Multivariate models: Granger causality, VAR and VECM models. Multivariate models: Granger causality, VAR and VECM models. Vilna, Lituania. Cummins, D., & Griepentrog, G. (1985). Forecasting Automobile Insurance and Paid Claim Costs using Economoetric and ARIMA Models. International Journal of Forecasting 1, 203-215. Eshel, G. (s.f.). The Yule Walker Equations for the AR Coefficients. Fasecolda. (s.f.). Fasecolda. Obtenido de Facecolda: https://fasecolda.com/cms/wp content/uploads/2019/08/15_efectos_en_el_pg_en_subestimar_la_reserva_de_ibnr.pdf Hernandez, S. (2015). Análisis de Series de Tiempo. Curso Regional Sobre Hoja de Balance de Alimentos, Series de Tiempo y Análisis de Política. Ciudad de México: CEPAL. Hyndman, R., & Khandakar, Y. (2008). Automatic Time Series Forecasting: Th forecast Package for R. Journal of Statistical Software, 8-12. Kang, H. (2013). The Prevention and Handling of the Misssing Data. Korean Journal Anesthesiology, 402-406. Kwiatkowski, D., Phillips, P., Schmidt, P., & Shin, Y. (1991). Testing the null hypothesis of stationarity against the alternative of a unit root. Journal of Econometrics, 159-178. Lazerri, F. (2021). Machine Learning for Time Series with Python. Indianapolis: Wiley. Lütkepohl, H. (2005). New Introduction to Multiple Time Series Analysis. Berlin: Springer. Office for National Statistics. (2014). Consumer Price Index Technical Manual. Londres: Office for National Statistics. Riofrio, J., Chang, O., Fuelagan, R., & Peluffo, D. (2020). Forecasting the Consumer Price Index of Ecuador a Comparative Study of Predictive Models. International Journal on Advanced Science Engineering Information Technology. Rohmah, F. (2021). Comparison Four Kernels of SVR to Predict Consumer Price Index. Journal of Physics: Conference Series. Shumway, R., & Stoffer, D. (2006). Time Series Analysis and its Applications. New York: Springer. Super Intendencia Financiera de Colombia. (Marzo de 2022). Super Intendencia Financiera de Colombia. Obtenido de https://www.superfinanciera.gov.co/inicio/informes-y-cifras/cifras/establecimientos de-credito/informacion-periodica/diaria/tasa-de-cambio-representativa-del-mercado-trm-60819 Wade, C. (2020). Hands-On Gradient Boosting with XGBoost and scikit-learn. Packt Publishing. 52 Wang, Y., Wang, B., & Xinyang, Z. (2012). A new application of the support vector regression on the construction of financial conditions index to CPI prediction . International Conference on Computational Science, 1263-1272. Werner, G., & Claudine, M. (2016). Basic Ratemakingx. CAS. Wikipedia. (Mayo de 2014). Wikipedia. Obtenido de Wikipedia: https://es.wikipedia.org/wiki/Error_cuadr%C3%A1tico_medio Zhang, L. (2021). Time series forecast of sales volume based on XGBoost. Journal of Physics