Combination forecasting method using Bayesian models and a metaheuristic, case study

Planning of demand forecasting for perishable products is important for any type of industry that manufactures or distributes, especially if it has a seasonal behavior and a difficult to predict variability. This paper proposes a metaheuristic based on Ant Colony Optimization (ACO) for the combinati...

Full description

Autores:
Higuita Alzate, David
Valencia Cárdenas, Marisol
Correa Morales, Juan Carlos
Tipo de recurso:
Article of investigation
Fecha de publicación:
2018
Institución:
Tecnológico de Antioquia
Repositorio:
Repositorio Tdea
Idioma:
spa
OAI Identifier:
oai:dspace.tdea.edu.co:tdea/2843
Acceso en línea:
https://dspace.tdea.edu.co/handle/tdea/2843
Palabra clave:
Forecasts
Productos perecederos
Perishable products
Produto perecível
Produit périssable
Statistics and probability
Estadística y probabilidad
Pronósticos
Optimization theory
Teoría de optimización
Bayesian statistics
Estadística Bayesiana
Rights
openAccess
License
https://creativecommons.org/licenses/by-nc-nd/4.0/
id RepoTdea2_a9a8a4fe8106c6ebfbb9ec6c127f091a
oai_identifier_str oai:dspace.tdea.edu.co:tdea/2843
network_acronym_str RepoTdea2
network_name_str Repositorio Tdea
repository_id_str
dc.title.none.fl_str_mv Combination forecasting method using Bayesian models and a metaheuristic, case study
dc.title.translated.none.fl_str_mv Método de combinación de pronósticos usando modelos Bayesianos y una metaheurística, caso de estudio
title Combination forecasting method using Bayesian models and a metaheuristic, case study
spellingShingle Combination forecasting method using Bayesian models and a metaheuristic, case study
Forecasts
Productos perecederos
Perishable products
Produto perecível
Produit périssable
Statistics and probability
Estadística y probabilidad
Pronósticos
Optimization theory
Teoría de optimización
Bayesian statistics
Estadística Bayesiana
title_short Combination forecasting method using Bayesian models and a metaheuristic, case study
title_full Combination forecasting method using Bayesian models and a metaheuristic, case study
title_fullStr Combination forecasting method using Bayesian models and a metaheuristic, case study
title_full_unstemmed Combination forecasting method using Bayesian models and a metaheuristic, case study
title_sort Combination forecasting method using Bayesian models and a metaheuristic, case study
dc.creator.fl_str_mv Higuita Alzate, David
Valencia Cárdenas, Marisol
Correa Morales, Juan Carlos
dc.contributor.author.none.fl_str_mv Higuita Alzate, David
Valencia Cárdenas, Marisol
Correa Morales, Juan Carlos
dc.subject.other.none.fl_str_mv Forecasts
topic Forecasts
Productos perecederos
Perishable products
Produto perecível
Produit périssable
Statistics and probability
Estadística y probabilidad
Pronósticos
Optimization theory
Teoría de optimización
Bayesian statistics
Estadística Bayesiana
dc.subject.agrovoc.none.fl_str_mv Productos perecederos
Perishable products
Produto perecível
Produit périssable
dc.subject.proposal.none.fl_str_mv Statistics and probability
Estadística y probabilidad
Pronósticos
Optimization theory
Teoría de optimización
Bayesian statistics
Estadística Bayesiana
description Planning of demand forecasting for perishable products is important for any type of industry that manufactures or distributes, especially if it has a seasonal behavior and a difficult to predict variability. This paper proposes a metaheuristic based on Ant Colony Optimization (ACO) for the combination of forecasts of multiple products, based on three models: Mixed Linear Model (MLM), Bayesian Regression Model with Innovation (BRM) and Dynamic Linear Bayesian Model (BDLM), which are part of the proposed combination whose process is based on minimizing the Mean of Absolute percentage Error (SMAPE) indicator. It is found that the BDLM and BRM methodologies obtain good results on an individual basis, being better BRM, however, the ACO algorithm designed yields a better result, facilitating an adequate prediction of the demand of several products of a company in the meat buffer sector. Keywords: statistics and probability; forecasts; optimization theory; Bayesian statistics.
publishDate 2018
dc.date.issued.none.fl_str_mv 2018
dc.date.accessioned.none.fl_str_mv 2023-05-01T19:20:02Z
dc.date.available.none.fl_str_mv 2023-05-01T19:20:02Z
dc.type.spa.fl_str_mv Artículo de revista
dc.type.coar.spa.fl_str_mv http://purl.org/coar/resource_type/c_2df8fbb1
dc.type.content.spa.fl_str_mv Text
dc.type.driver.spa.fl_str_mv info:eu-repo/semantics/article
dc.type.redcol.spa.fl_str_mv http://purl.org/redcol/resource_type/ART
dc.type.version.spa.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.coarversion.spa.fl_str_mv http://purl.org/coar/version/c_970fb48d4fbd8a85
format http://purl.org/coar/resource_type/c_2df8fbb1
status_str publishedVersion
dc.identifier.issn.spa.fl_str_mv 0012-7353
dc.identifier.uri.none.fl_str_mv https://dspace.tdea.edu.co/handle/tdea/2843
dc.identifier.eissn.spa.fl_str_mv 2346-2183
identifier_str_mv 0012-7353
2346-2183
url https://dspace.tdea.edu.co/handle/tdea/2843
dc.language.iso.spa.fl_str_mv spa
language spa
dc.relation.citationendpage.spa.fl_str_mv 345
dc.relation.citationissue.spa.fl_str_mv 207
dc.relation.citationstartpage.spa.fl_str_mv 337
dc.relation.citationvolume.spa.fl_str_mv 85
dc.relation.ispartofjournal.spa.fl_str_mv Dyna
dc.relation.references.spa.fl_str_mv Doganis, P., Alexandridis, A., Patrinos P. and Sarimveis, H., Time series sales forecasting for short shelf-life food products based on artificial neural networks and evolutionary computing. J. Food Eng. 75(2), pp. 196-204, 2006. DOI:10.1016/j.jfoodeng.2005.03.056
Vidal, C., Londoño, J.C. y Contreras, F., Aplicación de modelos de inventarios en una cadena de abastecimiento de productos de consumo masivo con una bodega y N puntos de venta. Ing. y Compet. 6(1), pp. 35-52, 2004.
Krajewski, L., Ritzman, L. and Malhotra, M., Administración de operaciones, 8th ed. 2008
Bowerman, B., Koehler, A. and O’Connell, R., Pronósticos, series de tiempo y regresión: un enfoque aplicado. México, DF. CENCAGE Learning, 2007
Congdon, P., Bayesian statistical modelling. London, England: Wiley Series in Probability and Statistics, 2002.
Montoya, A., Montoya, I. y Castellanos, O., Situación de la competitividad de las Pyme en Colombia : elementos actuales y retos. Agron. Colomb. 28 (1), pp. 107-117, 2010.
Valencia, M., Tróchez, J., Vanegas, J. y Restrepo, J., Modelo para el análisis de la quiebra financiera en Pymes agroindustriales antioqueñas. Apunt. del CENES. 35. Julio-Diciembre, pp. 147-168, 2016.
Hanke, J. y Wichern, D., Pronósticos en los negocios. Prentice Hall. 2006
Valencia, M., Correa, J.C., Díaz, F. and Ramírez, S., Aplicación de modelación bayesiana y optimización para pronósticos de demanda. Ing. y Desarro. Univ. del Norte. 32(2), pp. 179-199, 2014. DOI: 10.14482/inde.32.2.5403
Fei, X., Lu, C.-C. and Liu, K., A bayesian dynamic linear model approach for real-time short-term freeway travel time prediction. Transp. Res. Part C Emerg. Technol. 19(6), pp. 1306-1318, 2011. DOI: 10.1016/j.trc.2010.10.005
Sakauchi, T., Applying bayesian forecasting to predict new customers’ heating oil demand, 2011.
West, B., Welch K. and Galecki, A., Linear mixed models: a practical guide using statistical software. 2006. DOI: 10.1080/15598608.2012.695708
Valencia, M., Estimación en modelos lineales mixtos con datos continuos usando transformaciones y distribuciones no normales. Tesis de Maestría. 2010.
Hsiao, C. and S.K., Wan Is there an optimal forecast combination?. J. Econom. 178, PART 2, pp. 294-309, 2014. DOI: 10.1016/j.jeconom.2013.11.003
Chahkoutahi, F. and Khashei, M., A seasonal direct optimal hybrid model of computational intelligence and soft computing techniques for electricity load forecasting. Energy. 140, pp. 988-1004, 2017. DOI: 10.1016/j.energy.2017.09.009
Gao, W., Sarlak, V., Parsaei, M. R. and Ferdosi, M. Combination of fuzzy based on a meta-heuristic algorithm to predict electricity price in an electricity markets. Chem. Eng. Res. Des. 131, pp. 333-345, 2018. DOI: 10.1016/j.cherd.2017.09.021
Guerrero, L., Gómez, J.D., Zapata, D. and Valencia, M., Comparación de tres metaheurísticas para la optimización de inventarios con estimación de demanda. pp. 51-68, 2016.
Makridakis, S., Hibon, M. and Moser, C., Accuracy of forecasting: an empirical investigation. J. R. Stat. Society. 142(2), pp. 97-145, 1979. DOI: 10.2307/2345077
Makridakis, S., Wheelwright, S. and McGee, V., Forecasting, methods and applications, Second Ed. John Wiley & Sons, 1983
Simchi-Levi, D., Kaminski, P. and Simchi-Levi, E., Designing and managing the supply chain, 3rd ed. New York: McGraw-Hill, 2008.
Valencia, M., González, D. y Cardona, J., Metodología de un modelo de optimización para el pronóstico y manejo de inventarios usando el metaheurístico Tabú. Rev. Ing. 24(1), pp. 13-27, 2014. DOI: 10.15517/ring.v24i1.13771
Diebold, F.X. The past, present, and future of macroeconomic forecasting. J. Econ. Perspect. 12(2), pp. 175-192, 1998.
Medina, S. y García, J., Predicción de demanda de energía en Colombia mediante un sistema de inferencia difuso neuronal. Energética. 33, pp. 15-24, 2005. DOI: 10.15446/energetica
Keles, D., Scelle, J., Paraschiv, F. and Fichtner, W., Extended forecast methods for day-ahead electricity spot prices applying artificial neural networks. Appl. Energy. 162, pp. 218-230, 2016
Claveria, O. and Torra, S., Forecasting tourism demand to Catalonia: neural networks vs. time series models. Econ. Model. 36, pp. 220-228, 2014.
West, B., Welch, K. and Galecki, A., Linear mixed models: a practical guide using statistical software, first. 2006
Valencia, M., Estimación en modelos lineales mixtos con datos continuos usando transformaciones y distribuciones no normales. Tesis de grado. Universidad Nacional de Colombia, Sede Medellín. [en línea]. Disponible en: http://www.bdigital.unal.edu.co/1862/1/71680093.2010.pdf, 2010.
Barbosa, C., Queiroz, C. and Migon, H., A dynamic linear model with extended skew-normal for the initial distribution of the state parameter. Comput. Stat. Data Anal. 74, pp. 64-80, 2014. DOI: 10.1016/j.csda.2013.12.008
Oracle., The Bayesian approach to forecasting. September, 2006
Kociecki, A., Kolasa, M. and Rubaszek, M., A Bayesian method of combining judgmental and model-based density forecasts. Econ. Model. 29, pp. 1349-1355, 2012.
Gill, J., Bayesian methods for the social and behavioral sciences. Harvard University, 2007, pp. 9-11.
Valencia-Cárdenas, M., Dynamic model for the multiproduct inventory optimization with multivariate demand. Tesis de Doctorado. Universidad Nacional de Colombia, Sede Medellín, 2016
Zellner, A., An introduction to Bayesian inference in econometrics, Second. Wiley Classics Library, 1996
Story, R.E., An explanation of the effectiveness of latent semantic indexing by means of a Bayesian regression model. Inf. Process. Manag. 32(3), pp. 329-344, 1996. DOI: 10.1016/0306- 4573(95)00055-0
Castaño, E. y Melo, L.F., Métodos de combinación de pronósticos: una aplicación a la inflación colombiana. Borradores Econ. Banco de la República. 109, 1998
Bates J.M. and Granger, C.W., The combination of forecasts. Operational Research Quarterly. 20(4), pp. 451, 1969
Chan, C.K., Kingsman, B.G. and Wong, H., The value of combining forecasts in inventory management. A case study in banking. Eur. J. Oper. Res. 117, pp. 199-210, 1999
Bunn, D.W., Forecasting with more than one model. J. Forecast. 8(April), pp. 161-166, 1989.
Fouskakis, D. and Draper, D., Stochastic optimization: a review, Int. Stat. Rev. 70(3), pp. 315-349, 2002. DOI: 10.1111/j.1751- 5823.2002.tb00174.x
Silver, E., An overview of heuristic solution methods. Journal of the Operational Research Society. 55(9), pp. 936-956, DOI: 10.1057/palgrave.jors.2601758
Kapetanios, G., Marcellino, M. and Papailias, F., Forecasting inflation and GDP growth using heuristic optimisation of information criteria and variable reduction methods. Comput. Stat. Data Anal. 100, pp. 369-382, 2014. DOI: 10.1016/j.csda.2015.02.017
Fernández, I. de Viana, O., Cordón, Alonso, S. y Herrera, F., La metaheurística de optimización basada en colonias de hormigas: modelos y nuevos enfoques. Optim. Intel., pp. 261-314, 2004
Sen, T. and Mathur, H.D., A new approach to solve economic dispatch problem using a Hybrid ACO–ABC–HS optimization algorithm. Int. J. Electr. Power Energy Syst. 78, pp. 735-744, 2016. DOI: 10.1016/j.ijepes.2015.11.121
Kahraman, C., Kerre, E.E. and Bozbura, F.T., Uncertainty modeling in knowledge engineering and decision making. 7. World scientific, 2012. DOI: 10.1142/8564
Dorie, V., Package ‘blme’. pp. 1-8, 2015. Disponible en: https://cran.r-project.org/web/packages/blme/index.html
Petris, G., Petrone, S. and Campagnoli, P., Dynamic linear models with R. 2009. DOI: 10.1007/b135794
Petris, G., An R package for dynamic linear models. J. Stat. Softw. 36(12), pp. 1-16, 2010. DOI: 10.18637/jss.v036.i12
dc.rights.uri.spa.fl_str_mv https://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rights.license.spa.fl_str_mv Atribución-NoComercial-SinDerivadas 4.0 Internacional (CC BY-NC-ND 4.0)
dc.rights.accessrights.spa.fl_str_mv info:eu-repo/semantics/openAccess
dc.rights.coar.spa.fl_str_mv http://purl.org/coar/access_right/c_abf2
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-nd/4.0/
Atribución-NoComercial-SinDerivadas 4.0 Internacional (CC BY-NC-ND 4.0)
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.extent.spa.fl_str_mv 9 páginas
dc.format.mimetype.spa.fl_str_mv application/pdf
dc.coverage.city.none.fl_str_mv Medellín, Colombia
dc.publisher.spa.fl_str_mv Universidad Nacional de Colombia
dc.publisher.place.spa.fl_str_mv Colombia
dc.source.spa.fl_str_mv file:///C:/Users/user/Downloads/Metodo_de_combinacion_de_pronosticos_usando_modelo.pdf
institution Tecnológico de Antioquia
bitstream.url.fl_str_mv https://dspace.tdea.edu.co/bitstream/tdea/2843/1/Metodo_de_combinacion_de_pronosticos_usando_modelo.pdf
https://dspace.tdea.edu.co/bitstream/tdea/2843/2/license.txt
https://dspace.tdea.edu.co/bitstream/tdea/2843/3/Metodo_de_combinacion_de_pronosticos_usando_modelo.pdf.txt
https://dspace.tdea.edu.co/bitstream/tdea/2843/4/Metodo_de_combinacion_de_pronosticos_usando_modelo.pdf.jpg
bitstream.checksum.fl_str_mv 2adcd6f77af83af991de06f4271d25ff
2f9959eaf5b71fae44bbf9ec84150c7a
07b54edf4f725846683bb8313448b16e
73bcd6a829326e07d61cdb7a5e64f828
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
MD5
repository.name.fl_str_mv Repositorio Institucional Tecnologico de Antioquia
repository.mail.fl_str_mv bdigital@metabiblioteca.com
_version_ 1812189139550863360
spelling Higuita Alzate, Davidb7d1dcdd-aa54-4ca2-84ae-13de5a679bb6Valencia Cárdenas, Marisol7d8db2ff-5466-4ebb-a8b6-daf0bdc169d8Correa Morales, Juan Carlos80dd1582-58bc-447f-85ba-6aaadd85c30a2023-05-01T19:20:02Z2023-05-01T19:20:02Z20180012-7353https://dspace.tdea.edu.co/handle/tdea/28432346-2183Planning of demand forecasting for perishable products is important for any type of industry that manufactures or distributes, especially if it has a seasonal behavior and a difficult to predict variability. This paper proposes a metaheuristic based on Ant Colony Optimization (ACO) for the combination of forecasts of multiple products, based on three models: Mixed Linear Model (MLM), Bayesian Regression Model with Innovation (BRM) and Dynamic Linear Bayesian Model (BDLM), which are part of the proposed combination whose process is based on minimizing the Mean of Absolute percentage Error (SMAPE) indicator. It is found that the BDLM and BRM methodologies obtain good results on an individual basis, being better BRM, however, the ACO algorithm designed yields a better result, facilitating an adequate prediction of the demand of several products of a company in the meat buffer sector. Keywords: statistics and probability; forecasts; optimization theory; Bayesian statistics.La planeación de pronósticos de demanda de productos perecederos es importante para todo tipo de industria que los manufacture o distribuya, en especial, cuando ésta tiene un comportamiento estacional y variabilidad difícil de predecir. En este trabajo se propone una metaheurística basada en Optimización por Colonia de Hormigas (ACO) para la combinación de pronósticos de múltiples productos, basada en tres modelos: Modelo Lineal Mixto (MLM), Modelo de Regresión Bayesiana (BRM) y Modelo Bayesiano Lineal Dinámico (BDLM), los cuales hacen parte de la combinación propuesta cuyo proceso se basa en la minimización del indicador de Media de Error Absoluto Porcentual Simétrico (SMAPE). Se encuentra que las metodologías de BDLM y de BRM obtienen buenos resultados de forma individual siendo mejor esta última, no obstante, el algoritmo ACO diseñado arroja un mejor resultado, facilitando una adecuada predicción de demanda de varios productos de una empresa del sector de cárnicos. Palabras clave: estadística y probabilidad; pronósticos; teoría de optimización; estadística Bayesiana9 páginasapplication/pdfspaUniversidad Nacional de ColombiaColombiahttps://creativecommons.org/licenses/by-nc-nd/4.0/Atribución-NoComercial-SinDerivadas 4.0 Internacional (CC BY-NC-ND 4.0)info:eu-repo/semantics/openAccesshttp://purl.org/coar/access_right/c_abf2file:///C:/Users/user/Downloads/Metodo_de_combinacion_de_pronosticos_usando_modelo.pdfForecastsProductos perecederosPerishable productsProduto perecívelProduit périssableStatistics and probabilityEstadística y probabilidadPronósticosOptimization theoryTeoría de optimizaciónBayesian statisticsEstadística BayesianaCombination forecasting method using Bayesian models and a metaheuristic, case studyMétodo de combinación de pronósticos usando modelos Bayesianos y una metaheurística, caso de estudioArtículo de revistahttp://purl.org/coar/resource_type/c_2df8fbb1Textinfo:eu-repo/semantics/articlehttp://purl.org/redcol/resource_type/ARTinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/version/c_970fb48d4fbd8a85Medellín, Colombia34520733785DynaDoganis, P., Alexandridis, A., Patrinos P. and Sarimveis, H., Time series sales forecasting for short shelf-life food products based on artificial neural networks and evolutionary computing. J. Food Eng. 75(2), pp. 196-204, 2006. DOI:10.1016/j.jfoodeng.2005.03.056Vidal, C., Londoño, J.C. y Contreras, F., Aplicación de modelos de inventarios en una cadena de abastecimiento de productos de consumo masivo con una bodega y N puntos de venta. Ing. y Compet. 6(1), pp. 35-52, 2004.Krajewski, L., Ritzman, L. and Malhotra, M., Administración de operaciones, 8th ed. 2008Bowerman, B., Koehler, A. and O’Connell, R., Pronósticos, series de tiempo y regresión: un enfoque aplicado. México, DF. CENCAGE Learning, 2007Congdon, P., Bayesian statistical modelling. London, England: Wiley Series in Probability and Statistics, 2002.Montoya, A., Montoya, I. y Castellanos, O., Situación de la competitividad de las Pyme en Colombia : elementos actuales y retos. Agron. Colomb. 28 (1), pp. 107-117, 2010.Valencia, M., Tróchez, J., Vanegas, J. y Restrepo, J., Modelo para el análisis de la quiebra financiera en Pymes agroindustriales antioqueñas. Apunt. del CENES. 35. Julio-Diciembre, pp. 147-168, 2016.Hanke, J. y Wichern, D., Pronósticos en los negocios. Prentice Hall. 2006Valencia, M., Correa, J.C., Díaz, F. and Ramírez, S., Aplicación de modelación bayesiana y optimización para pronósticos de demanda. Ing. y Desarro. Univ. del Norte. 32(2), pp. 179-199, 2014. DOI: 10.14482/inde.32.2.5403Fei, X., Lu, C.-C. and Liu, K., A bayesian dynamic linear model approach for real-time short-term freeway travel time prediction. Transp. Res. Part C Emerg. Technol. 19(6), pp. 1306-1318, 2011. DOI: 10.1016/j.trc.2010.10.005Sakauchi, T., Applying bayesian forecasting to predict new customers’ heating oil demand, 2011.West, B., Welch K. and Galecki, A., Linear mixed models: a practical guide using statistical software. 2006. DOI: 10.1080/15598608.2012.695708Valencia, M., Estimación en modelos lineales mixtos con datos continuos usando transformaciones y distribuciones no normales. Tesis de Maestría. 2010.Hsiao, C. and S.K., Wan Is there an optimal forecast combination?. J. Econom. 178, PART 2, pp. 294-309, 2014. DOI: 10.1016/j.jeconom.2013.11.003Chahkoutahi, F. and Khashei, M., A seasonal direct optimal hybrid model of computational intelligence and soft computing techniques for electricity load forecasting. Energy. 140, pp. 988-1004, 2017. DOI: 10.1016/j.energy.2017.09.009Gao, W., Sarlak, V., Parsaei, M. R. and Ferdosi, M. Combination of fuzzy based on a meta-heuristic algorithm to predict electricity price in an electricity markets. Chem. Eng. Res. Des. 131, pp. 333-345, 2018. DOI: 10.1016/j.cherd.2017.09.021Guerrero, L., Gómez, J.D., Zapata, D. and Valencia, M., Comparación de tres metaheurísticas para la optimización de inventarios con estimación de demanda. pp. 51-68, 2016.Makridakis, S., Hibon, M. and Moser, C., Accuracy of forecasting: an empirical investigation. J. R. Stat. Society. 142(2), pp. 97-145, 1979. DOI: 10.2307/2345077Makridakis, S., Wheelwright, S. and McGee, V., Forecasting, methods and applications, Second Ed. John Wiley & Sons, 1983Simchi-Levi, D., Kaminski, P. and Simchi-Levi, E., Designing and managing the supply chain, 3rd ed. New York: McGraw-Hill, 2008.Valencia, M., González, D. y Cardona, J., Metodología de un modelo de optimización para el pronóstico y manejo de inventarios usando el metaheurístico Tabú. Rev. Ing. 24(1), pp. 13-27, 2014. DOI: 10.15517/ring.v24i1.13771Diebold, F.X. The past, present, and future of macroeconomic forecasting. J. Econ. Perspect. 12(2), pp. 175-192, 1998.Medina, S. y García, J., Predicción de demanda de energía en Colombia mediante un sistema de inferencia difuso neuronal. Energética. 33, pp. 15-24, 2005. DOI: 10.15446/energeticaKeles, D., Scelle, J., Paraschiv, F. and Fichtner, W., Extended forecast methods for day-ahead electricity spot prices applying artificial neural networks. Appl. Energy. 162, pp. 218-230, 2016Claveria, O. and Torra, S., Forecasting tourism demand to Catalonia: neural networks vs. time series models. Econ. Model. 36, pp. 220-228, 2014.West, B., Welch, K. and Galecki, A., Linear mixed models: a practical guide using statistical software, first. 2006Valencia, M., Estimación en modelos lineales mixtos con datos continuos usando transformaciones y distribuciones no normales. Tesis de grado. Universidad Nacional de Colombia, Sede Medellín. [en línea]. Disponible en: http://www.bdigital.unal.edu.co/1862/1/71680093.2010.pdf, 2010.Barbosa, C., Queiroz, C. and Migon, H., A dynamic linear model with extended skew-normal for the initial distribution of the state parameter. Comput. Stat. Data Anal. 74, pp. 64-80, 2014. DOI: 10.1016/j.csda.2013.12.008Oracle., The Bayesian approach to forecasting. September, 2006Kociecki, A., Kolasa, M. and Rubaszek, M., A Bayesian method of combining judgmental and model-based density forecasts. Econ. Model. 29, pp. 1349-1355, 2012.Gill, J., Bayesian methods for the social and behavioral sciences. Harvard University, 2007, pp. 9-11.Valencia-Cárdenas, M., Dynamic model for the multiproduct inventory optimization with multivariate demand. Tesis de Doctorado. Universidad Nacional de Colombia, Sede Medellín, 2016Zellner, A., An introduction to Bayesian inference in econometrics, Second. Wiley Classics Library, 1996Story, R.E., An explanation of the effectiveness of latent semantic indexing by means of a Bayesian regression model. Inf. Process. Manag. 32(3), pp. 329-344, 1996. DOI: 10.1016/0306- 4573(95)00055-0Castaño, E. y Melo, L.F., Métodos de combinación de pronósticos: una aplicación a la inflación colombiana. Borradores Econ. Banco de la República. 109, 1998Bates J.M. and Granger, C.W., The combination of forecasts. Operational Research Quarterly. 20(4), pp. 451, 1969Chan, C.K., Kingsman, B.G. and Wong, H., The value of combining forecasts in inventory management. A case study in banking. Eur. J. Oper. Res. 117, pp. 199-210, 1999Bunn, D.W., Forecasting with more than one model. J. Forecast. 8(April), pp. 161-166, 1989.Fouskakis, D. and Draper, D., Stochastic optimization: a review, Int. Stat. Rev. 70(3), pp. 315-349, 2002. DOI: 10.1111/j.1751- 5823.2002.tb00174.xSilver, E., An overview of heuristic solution methods. Journal of the Operational Research Society. 55(9), pp. 936-956, DOI: 10.1057/palgrave.jors.2601758Kapetanios, G., Marcellino, M. and Papailias, F., Forecasting inflation and GDP growth using heuristic optimisation of information criteria and variable reduction methods. Comput. Stat. Data Anal. 100, pp. 369-382, 2014. DOI: 10.1016/j.csda.2015.02.017Fernández, I. de Viana, O., Cordón, Alonso, S. y Herrera, F., La metaheurística de optimización basada en colonias de hormigas: modelos y nuevos enfoques. Optim. Intel., pp. 261-314, 2004Sen, T. and Mathur, H.D., A new approach to solve economic dispatch problem using a Hybrid ACO–ABC–HS optimization algorithm. Int. J. Electr. Power Energy Syst. 78, pp. 735-744, 2016. DOI: 10.1016/j.ijepes.2015.11.121Kahraman, C., Kerre, E.E. and Bozbura, F.T., Uncertainty modeling in knowledge engineering and decision making. 7. World scientific, 2012. DOI: 10.1142/8564Dorie, V., Package ‘blme’. pp. 1-8, 2015. Disponible en: https://cran.r-project.org/web/packages/blme/index.htmlPetris, G., Petrone, S. and Campagnoli, P., Dynamic linear models with R. 2009. DOI: 10.1007/b135794Petris, G., An R package for dynamic linear models. J. Stat. Softw. 36(12), pp. 1-16, 2010. DOI: 10.18637/jss.v036.i12ORIGINALMetodo_de_combinacion_de_pronosticos_usando_modelo.pdfMetodo_de_combinacion_de_pronosticos_usando_modelo.pdfapplication/pdf855605https://dspace.tdea.edu.co/bitstream/tdea/2843/1/Metodo_de_combinacion_de_pronosticos_usando_modelo.pdf2adcd6f77af83af991de06f4271d25ffMD51open accessLICENSElicense.txtlicense.txttext/plain; charset=utf-814828https://dspace.tdea.edu.co/bitstream/tdea/2843/2/license.txt2f9959eaf5b71fae44bbf9ec84150c7aMD52open accessTEXTMetodo_de_combinacion_de_pronosticos_usando_modelo.pdf.txtMetodo_de_combinacion_de_pronosticos_usando_modelo.pdf.txtExtracted texttext/plain47183https://dspace.tdea.edu.co/bitstream/tdea/2843/3/Metodo_de_combinacion_de_pronosticos_usando_modelo.pdf.txt07b54edf4f725846683bb8313448b16eMD53open accessTHUMBNAILMetodo_de_combinacion_de_pronosticos_usando_modelo.pdf.jpgMetodo_de_combinacion_de_pronosticos_usando_modelo.pdf.jpgGenerated Thumbnailimage/jpeg15554https://dspace.tdea.edu.co/bitstream/tdea/2843/4/Metodo_de_combinacion_de_pronosticos_usando_modelo.pdf.jpg73bcd6a829326e07d61cdb7a5e64f828MD54open accesstdea/2843oai:dspace.tdea.edu.co:tdea/28432023-05-02 03:00:21.637An error occurred on the license name.|||https://creativecommons.org/licenses/by-nc-nd/4.0/open accessRepositorio Institucional Tecnologico de Antioquiabdigital@metabiblioteca.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