Pronósticos del precio del ganado de primera calidad en Subastar S.A. - Montería: una comparativa entre modelos de series de tiempo clásicos, redes neuronales artificiales y modelos híbridos
Este estudio analizó y comparó modelos de series de tiempo clásicos, redes neuronales artificiales y métodos híbridos para pronosticar el precio del ganado de primera calidad en Subastar S.A., Montería. Se destacó la importancia económica del sector ganadero en Córdoba y la evolución de la comercial...
- Autores:
-
Miranda Urango, Yehison Elías
Pérez Cuadrado, Isaac Manuel
- Tipo de recurso:
- Trabajo de grado de pregrado
- Fecha de publicación:
- 2024
- Institución:
- Universidad de Córdoba
- Repositorio:
- Repositorio Institucional Unicórdoba
- Idioma:
- spa
- OAI Identifier:
- oai:repositorio.unicordoba.edu.co:ucordoba/8809
- Acceso en línea:
- https://repositorio.unicordoba.edu.co/handle/ucordoba/8809
https://repositorio.unicordoba.edu.co
- Palabra clave:
- Modelos de series de tiempo clasicos
Aprendizaje automatico
Redes neuronales
Modelos hibridos
Classic time series models
Machine Learning
Neural Network
Hybrid models
- Rights
- openAccess
- License
- Copyright Universidad de Córdoba, 2024
| id |
UCORDOBA2_aaf49e77bb47a27468c63fd76a2d9ef0 |
|---|---|
| oai_identifier_str |
oai:repositorio.unicordoba.edu.co:ucordoba/8809 |
| network_acronym_str |
UCORDOBA2 |
| network_name_str |
Repositorio Institucional Unicórdoba |
| repository_id_str |
|
| dc.title.spa.fl_str_mv |
Pronósticos del precio del ganado de primera calidad en Subastar S.A. - Montería: una comparativa entre modelos de series de tiempo clásicos, redes neuronales artificiales y modelos híbridos |
| title |
Pronósticos del precio del ganado de primera calidad en Subastar S.A. - Montería: una comparativa entre modelos de series de tiempo clásicos, redes neuronales artificiales y modelos híbridos |
| spellingShingle |
Pronósticos del precio del ganado de primera calidad en Subastar S.A. - Montería: una comparativa entre modelos de series de tiempo clásicos, redes neuronales artificiales y modelos híbridos Modelos de series de tiempo clasicos Aprendizaje automatico Redes neuronales Modelos hibridos Classic time series models Machine Learning Neural Network Hybrid models |
| title_short |
Pronósticos del precio del ganado de primera calidad en Subastar S.A. - Montería: una comparativa entre modelos de series de tiempo clásicos, redes neuronales artificiales y modelos híbridos |
| title_full |
Pronósticos del precio del ganado de primera calidad en Subastar S.A. - Montería: una comparativa entre modelos de series de tiempo clásicos, redes neuronales artificiales y modelos híbridos |
| title_fullStr |
Pronósticos del precio del ganado de primera calidad en Subastar S.A. - Montería: una comparativa entre modelos de series de tiempo clásicos, redes neuronales artificiales y modelos híbridos |
| title_full_unstemmed |
Pronósticos del precio del ganado de primera calidad en Subastar S.A. - Montería: una comparativa entre modelos de series de tiempo clásicos, redes neuronales artificiales y modelos híbridos |
| title_sort |
Pronósticos del precio del ganado de primera calidad en Subastar S.A. - Montería: una comparativa entre modelos de series de tiempo clásicos, redes neuronales artificiales y modelos híbridos |
| dc.creator.fl_str_mv |
Miranda Urango, Yehison Elías Pérez Cuadrado, Isaac Manuel |
| dc.contributor.advisor.none.fl_str_mv |
Treco Hernández, Manuel |
| dc.contributor.author.none.fl_str_mv |
Miranda Urango, Yehison Elías Pérez Cuadrado, Isaac Manuel |
| dc.contributor.educationalvalidator.none.fl_str_mv |
Treco Hernandez, Manuel |
| dc.contributor.jury.none.fl_str_mv |
Caicedo Castro, Isaac Bernardo Bru Cordero, Osnamir Elias |
| dc.subject.proposal.spa.fl_str_mv |
Modelos de series de tiempo clasicos Aprendizaje automatico Redes neuronales Modelos hibridos |
| topic |
Modelos de series de tiempo clasicos Aprendizaje automatico Redes neuronales Modelos hibridos Classic time series models Machine Learning Neural Network Hybrid models |
| dc.subject.keywords.eng.fl_str_mv |
Classic time series models Machine Learning Neural Network Hybrid models |
| description |
Este estudio analizó y comparó modelos de series de tiempo clásicos, redes neuronales artificiales y métodos híbridos para pronosticar el precio del ganado de primera calidad en Subastar S.A., Montería. Se destacó la importancia económica del sector ganadero en Córdoba y la evolución de la comercialización a través de subastas y plataformas virtuales. Además, se exploró el impacto de la inteligencia artificial en la predicción de precios, con énfasis en la metodología de Box-Jenkins y las redes neuronales. Se encontró que los modelos de redes neuronales híbridos CNN-LSTM y el modelo Transformer fueron los que arrojaron mejores resultados. El objetivo fue identificar el modelo más adecuado para mejorar la planificación económica y reducir riesgos financieros. |
| publishDate |
2024 |
| dc.date.accessioned.none.fl_str_mv |
2024-12-11T15:11:27Z |
| dc.date.available.none.fl_str_mv |
2024-12-11T15:11:27Z |
| dc.date.issued.none.fl_str_mv |
2024-12-09 |
| dc.type.none.fl_str_mv |
Trabajo de grado - Pregrado |
| dc.type.driver.none.fl_str_mv |
info:eu-repo/semantics/bachelorThesis |
| dc.type.coar.none.fl_str_mv |
http://purl.org/coar/resource_type/c_7a1f |
| dc.type.version.none.fl_str_mv |
info:eu-repo/semantics/acceptedVersion |
| dc.type.content.none.fl_str_mv |
Text |
| format |
http://purl.org/coar/resource_type/c_7a1f |
| status_str |
acceptedVersion |
| dc.identifier.uri.none.fl_str_mv |
https://repositorio.unicordoba.edu.co/handle/ucordoba/8809 |
| dc.identifier.instname.none.fl_str_mv |
Universidad de Córdoba |
| dc.identifier.reponame.none.fl_str_mv |
Repositorio Universidad de Córdoba |
| dc.identifier.repourl.none.fl_str_mv |
https://repositorio.unicordoba.edu.co |
| url |
https://repositorio.unicordoba.edu.co/handle/ucordoba/8809 https://repositorio.unicordoba.edu.co |
| identifier_str_mv |
Universidad de Córdoba Repositorio Universidad de Córdoba |
| dc.language.iso.none.fl_str_mv |
spa |
| language |
spa |
| dc.relation.references.none.fl_str_mv |
Anderson, O.D (1976). Time Series Analysis and forecasting( The Box-Jenkins Approach). Butterworth, londres.p.116. Ballesteros, F., y Cogollo, M. (2023). Estructuras híbridas para el modelado y pron´ostico de series temporales: metodologías y aplicaciones. Box, G. E. P., y Jenkins, G. M. (1976). Time series analysis. Forecasting and control. Holsen-Day series in time series analysis.p.574. Blyth, C. R. (1972). ≪On Simpson’s Paraclox and the Sure-Thing Principie≫. Journal of the American Statistical Association,V. 67, 338, pp. 364-366. Brockwell P. J. and Davis R. A. (2016). Introduction to time series and forecasting (3rd ed). New York, USA, Springer. Brownlee, J. (2017). Long Short-Term Memory Networks With Python, Machine Learning Mastery. Brownlee, J. (2019). Deep Learning for Time Series Forecasting: Predict the Future with MLPs, CNNs and LSTMs in Python, Machine Learning Mastery. Caicedo, E y López, J. (2009). Una aproximación práctica a las Redes Neuronales Artificiales. Cali: Universidad del Valle. Chambi, J. y Conde, S. (2021). Modelo de predicción mensual de infección respiratoria aguda (ira) en niños menores de 5 años en la micro red el descanso–cusco, 2014-2019. Cogollo, M. R., Gonz´alez-Parra, G., y Arenas, A. J. (2021). Modeling and forecasting cases of rsv using artificial neural networks. Mathematics, 9(22), 2958. Dorffner, G. (1996), Neural network for time series processing. Technical report, University of Vienna and Autrian research institute for artificial intelligence. Guerrero, V.(2003). An´alisis estad´ıstico de series de tiempo economicas, 2ª Edici ´on THOMSON. M´exico, 2003. p 107-175. Haykin, S. S. (1999). Neural Networks: A Comprehensive Foundation (2nd ed.). Prentice Hall, Englewood Cliffs, NJ. Hermans, M. y Schrauwen, B. (2013). Training and analyzing deep recurrent neural networks, Technical report, Ghent University. Hinton, G., Srivastava, N., Krizhevsky, A., Sutskever, I. y Salakhutdinov, R. (2012), Improving neural networks by preventing co-adaptation of feature detectors, Technical report, Department of Computer Science, University of Toronto. Hyndman, R. y Athanasopoulos, G. (2018). Forecasting: Principles and practice (2nd ed.). Australia: OTexts. Hochreiter, S and Schmidhuber, J. (1997). Long Short-term Memory. Neural computation, 9, 1735-1780. Jozefowicz, R, Zaremba, W y Sutskever, I. (2015). “An Empirical Exploration of Recurrent Network Architecture”. En: Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume37. ICML’15. Lille,France: JMLR.org, 2342–2350. Kazemi, S. M., Goel, R., Eghbali, S., Ramanan, J., Sahota, J, Thakur, S., Wu, S., Smyth, C., Poupart, P. y Brubaker, M.. (2019). Time2Vec:Learning a Vector Representation of Time. arXiv:1907.05321. Kelleher, J. D. (2019). Deep learning. MIT press. Knief, U., y Forstmeier, W. (2021). Violating the normality assumption may be the lesser of two evils. Behavior Research Methods, 53(6), 2576–2590. Lindholm, A., Wahlstrom, N., Lindsten, F. & Schon, T. (2019). Supervised machine learning lecture notes for the statistical machine learning course. Technical report, Uppsala University. Lopez, R.(2016). Series de tiempo con Python. Recuperado de https://relopezbriega.github.io/blog/2016/09/26/series-de-tiempo-con-python/ Malhotra, P., Vig, L., Shroff, G. y Agarwal, P. (2015). “Long short term memory networks for anomaly detection in time series”, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. pp. 89–94. Ospina, R., Gondim, J. A. M., Leiva, V., y Castro, C. (2023). An overview of forecast analysis with arima models during the covid-19 pandemic: Methodology and case study in brazil. Mathematics, 11(14). Descargado de https://www.mdpi.com 2227-7390/11/14/3069 doi: 10.3390/math11143069. Peña, D. (2005). Análisis de series temporales. Alianza editorial. Phi, M. (2018), ‘Illustrated guide to lstm’s and gru’s: A step by step explanation’. https://towardsdatascience.com/illustrated-guide-to-lstms-and-gru-s-a-stepby- step-explanation-44e9eb85bf21, Web; accedido el 01-07-2020. Sak, H., Senior, A. y Beaufays, F. (2014). “Long short-term memory recurrent neural network architectures for large scale acoustic modeling”. INTERSPEECH pp. 338–342. T´ellez, C. & Morales, M. (2016). Modelos estad´ısticos lineales. Con aplicaciones en R, Ediciones de la U, Bogot´a. Trifa, A., Sbai, A. & Chaari, W. (2017). ’Enhancing assessment of personalized multi-agent system through convlstm’, Procedia Computer Science 112, 249–259. Tsay, R. S., y Tiao, G. C. (1984). Consistent estimates of autoregressive parameters and extended sample autocorrelation function for stationary and nonstationary arma models. Journal of the American Statistical Association, 79(385), 84-96. doi: 10.1080/01621459.1984.10477068. Tomek, W. y Robinson, K. (2005). Agricultural Product Prices. Cornell University Press. Valencia, M., Yañez, C. y Sanchez, L. (2006).Algoritmo blackpropagation para Redes Neuronales: conceptos y aplicaciones. M´exico. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N.,Kaiser, L. y Polosukhin, I.. Attention Is All You Need. 2017. arXiv: 1706. 03762. Wagner, R. H. (1982).“A noncooperative solution to a two-person bargaining game”. Unpublished paper. Weaver, R. y W. Natcher,W. (2000). Has market reform exposed farmers to greater price volatility?. In Farm Economics, Cooperative Extension Service, US Department of Agriculture. College Station, PA:Pennsylvania State University. Yang, j., Nguyen, M., San, P., Li, X. y Krishnaswamy, S. (2015). “Deep convolutional neural networks on multichannel time series for human activity recognition”, Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence pp. 3995–4001. Yu, G., Feng, H., Feng, S., Zhao, J., y Xu, J. (2021). Forecasting hand-footand- mouth disease cases using wavelet-based sarima–nnar hybrid model. PLoS one, 16(2), e0246673. Yule, G.U. (1927). On a method of investigating the periodicities of disturbed series, with special reference to Wolfer’s sunspot numbers. Philosophical Transactions of the Royal Society (A), 226, 267-298. |
| dc.rights.none.fl_str_mv |
Copyright Universidad de Córdoba, 2024 |
| dc.rights.uri.none.fl_str_mv |
https://creativecommons.org/licenses/by-nc-sa/4.0/ |
| dc.rights.license.none.fl_str_mv |
Atribución-NoComercial-CompartirIgual 4.0 Internacional (CC BY-NC-SA 4.0) |
| dc.rights.accessrights.none.fl_str_mv |
info:eu-repo/semantics/openAccess |
| dc.rights.coar.none.fl_str_mv |
http://purl.org/coar/access_right/c_abf2 |
| rights_invalid_str_mv |
Copyright Universidad de Córdoba, 2024 https://creativecommons.org/licenses/by-nc-sa/4.0/ Atribución-NoComercial-CompartirIgual 4.0 Internacional (CC BY-NC-SA 4.0) http://purl.org/coar/access_right/c_abf2 |
| eu_rights_str_mv |
openAccess |
| dc.format.mimetype.none.fl_str_mv |
application/pdf |
| dc.publisher.none.fl_str_mv |
Universidad de Córdoba |
| dc.publisher.faculty.none.fl_str_mv |
Facultad de Ciencias Básicas |
| dc.publisher.place.none.fl_str_mv |
Montería, Córdoba, Colombia |
| dc.publisher.program.none.fl_str_mv |
Estadística |
| publisher.none.fl_str_mv |
Universidad de Córdoba |
| institution |
Universidad de Córdoba |
| bitstream.url.fl_str_mv |
https://repositorio.unicordoba.edu.co/bitstreams/5e03307b-4551-454b-a9d0-18cbe8d7d929/download https://repositorio.unicordoba.edu.co/bitstreams/7ac5a632-c3ad-4b7f-b9e4-461422a15814/download https://repositorio.unicordoba.edu.co/bitstreams/8d6e1f98-6a82-4f94-931e-8d76b9a7a037/download https://repositorio.unicordoba.edu.co/bitstreams/d7cf3872-be8d-4c36-9902-555f044a07ca/download https://repositorio.unicordoba.edu.co/bitstreams/716ed71e-e355-4de3-b9c5-a011a3a1c14f/download https://repositorio.unicordoba.edu.co/bitstreams/c95632a8-d4ba-4544-9025-a719121a983a/download https://repositorio.unicordoba.edu.co/bitstreams/a3854943-7575-40ad-b06d-9e178dc4da72/download |
| bitstream.checksum.fl_str_mv |
73a5432e0b76442b22b026844140d683 983c6717d6a19af31f38256497fe92af 55d62a0adf0d2b3c844be6a6ecad664b e02e584c7e92b63bc0fa58144684a50e b90cbcdf51c3553201af6cd3f43f2973 c44c237e66251a20f86888e1e6bf4039 01981055f6e65e53839434d6d0dc67b5 |
| bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 MD5 MD5 MD5 |
| repository.name.fl_str_mv |
Repositorio Universidad de Córdoba |
| repository.mail.fl_str_mv |
bdigital@metabiblioteca.com |
| _version_ |
1839636044090179584 |
| spelling |
Treco Hernández, Manuel7937b3ab-380c-460c-aedb-10faaccab95e-1Miranda Urango, Yehison Elías89dbd6a8-f30d-4eed-9e9c-2410ecc8828c-1Pérez Cuadrado, Isaac Manuel5f96754b-a4c8-46c5-ad9d-0b277ffbbdb6-1Treco Hernandez, ManuelCaicedo Castro, Isaac Bernardof5a99141-637c-42dd-b13a-f31a8778f50a-1Bru Cordero, Osnamir Elias511500de-e81b-4eed-ab27-5661839aa3ca6002024-12-11T15:11:27Z2024-12-11T15:11:27Z2024-12-09https://repositorio.unicordoba.edu.co/handle/ucordoba/8809Universidad de CórdobaRepositorio Universidad de Córdobahttps://repositorio.unicordoba.edu.coEste estudio analizó y comparó modelos de series de tiempo clásicos, redes neuronales artificiales y métodos híbridos para pronosticar el precio del ganado de primera calidad en Subastar S.A., Montería. Se destacó la importancia económica del sector ganadero en Córdoba y la evolución de la comercialización a través de subastas y plataformas virtuales. Además, se exploró el impacto de la inteligencia artificial en la predicción de precios, con énfasis en la metodología de Box-Jenkins y las redes neuronales. Se encontró que los modelos de redes neuronales híbridos CNN-LSTM y el modelo Transformer fueron los que arrojaron mejores resultados. El objetivo fue identificar el modelo más adecuado para mejorar la planificación económica y reducir riesgos financieros.This study analyzed and compared classical time series models, artificial neural networks, and hybrid methods to forecast the price of prime cattle at Subastar S.A., Montería. The economic importance of the livestock sector in Córdoba and the evolution of commercialization through auctions and virtual platforms was highlighted. Additionally, the impact of artificial intelligence on price prediction was explored, with an emphasis on the Box-Jenkins methodology and neural networks. The study found that hybrid CNN-LSTM neural network models and the Transformer model yielded the best results. The objective was to identify the most suitable model to improve economic planning and reduce financial risks1. Introducción.2. Objetivos.3. Marco Teorico.4. Materiales y métodos.5. Resultados6. ConclusionesA. Anexos: Software utilizadosTrabajo presentado como requisito parcial para obtener el titulo de EstadísticoPregradoEstadístico(a)Trabajos de Investigación y/o Extensiónapplication/pdfspaUniversidad de CórdobaFacultad de Ciencias BásicasMontería, Córdoba, ColombiaEstadísticaCopyright Universidad de Córdoba, 2024https://creativecommons.org/licenses/by-nc-sa/4.0/Atribución-NoComercial-CompartirIgual 4.0 Internacional (CC BY-NC-SA 4.0)info:eu-repo/semantics/openAccesshttp://purl.org/coar/access_right/c_abf2Pronósticos del precio del ganado de primera calidad en Subastar S.A. - Montería: una comparativa entre modelos de series de tiempo clásicos, redes neuronales artificiales y modelos híbridosTrabajo de grado - Pregradoinfo:eu-repo/semantics/bachelorThesishttp://purl.org/coar/resource_type/c_7a1finfo:eu-repo/semantics/acceptedVersionTextAnderson, O.D (1976). Time Series Analysis and forecasting( The Box-Jenkins Approach). Butterworth, londres.p.116.Ballesteros, F., y Cogollo, M. (2023). Estructuras híbridas para el modelado y pron´ostico de series temporales: metodologías y aplicaciones.Box, G. E. P., y Jenkins, G. M. (1976). Time series analysis. Forecasting and control. Holsen-Day series in time series analysis.p.574.Blyth, C. R. (1972). ≪On Simpson’s Paraclox and the Sure-Thing Principie≫. Journal of the American Statistical Association,V. 67, 338, pp. 364-366.Brockwell P. J. and Davis R. A. (2016). Introduction to time series and forecasting (3rd ed). New York, USA, Springer.Brownlee, J. (2017). Long Short-Term Memory Networks With Python, Machine Learning Mastery.Brownlee, J. (2019). Deep Learning for Time Series Forecasting: Predict the Future with MLPs, CNNs and LSTMs in Python, Machine Learning Mastery.Caicedo, E y López, J. (2009). Una aproximación práctica a las Redes Neuronales Artificiales. Cali: Universidad del Valle.Chambi, J. y Conde, S. (2021). Modelo de predicción mensual de infección respiratoria aguda (ira) en niños menores de 5 años en la micro red el descanso–cusco, 2014-2019.Cogollo, M. R., Gonz´alez-Parra, G., y Arenas, A. J. (2021). Modeling and forecasting cases of rsv using artificial neural networks. Mathematics, 9(22), 2958.Dorffner, G. (1996), Neural network for time series processing. Technical report, University of Vienna and Autrian research institute for artificial intelligence.Guerrero, V.(2003). An´alisis estad´ıstico de series de tiempo economicas, 2ª Edici ´on THOMSON. M´exico, 2003. p 107-175.Haykin, S. S. (1999). Neural Networks: A Comprehensive Foundation (2nd ed.). Prentice Hall, Englewood Cliffs, NJ.Hermans, M. y Schrauwen, B. (2013). Training and analyzing deep recurrent neural networks, Technical report, Ghent University.Hinton, G., Srivastava, N., Krizhevsky, A., Sutskever, I. y Salakhutdinov, R. (2012), Improving neural networks by preventing co-adaptation of feature detectors, Technical report, Department of Computer Science, University of Toronto.Hyndman, R. y Athanasopoulos, G. (2018). Forecasting: Principles and practice (2nd ed.). Australia: OTexts.Hochreiter, S and Schmidhuber, J. (1997). Long Short-term Memory. Neural computation, 9, 1735-1780.Jozefowicz, R, Zaremba, W y Sutskever, I. (2015). “An Empirical Exploration of Recurrent Network Architecture”. En: Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume37. ICML’15. Lille,France: JMLR.org, 2342–2350.Kazemi, S. M., Goel, R., Eghbali, S., Ramanan, J., Sahota, J, Thakur, S., Wu, S., Smyth, C., Poupart, P. y Brubaker, M.. (2019). Time2Vec:Learning a Vector Representation of Time. arXiv:1907.05321.Kelleher, J. D. (2019). Deep learning. MIT press.Knief, U., y Forstmeier, W. (2021). Violating the normality assumption may be the lesser of two evils. Behavior Research Methods, 53(6), 2576–2590.Lindholm, A., Wahlstrom, N., Lindsten, F. & Schon, T. (2019). Supervised machine learning lecture notes for the statistical machine learning course. Technical report, Uppsala University.Lopez, R.(2016). Series de tiempo con Python. Recuperado de https://relopezbriega.github.io/blog/2016/09/26/series-de-tiempo-con-python/Malhotra, P., Vig, L., Shroff, G. y Agarwal, P. (2015). “Long short term memory networks for anomaly detection in time series”, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. pp. 89–94.Ospina, R., Gondim, J. A. M., Leiva, V., y Castro, C. (2023). An overview of forecast analysis with arima models during the covid-19 pandemic: Methodology and case study in brazil. Mathematics, 11(14). Descargado de https://www.mdpi.com 2227-7390/11/14/3069 doi: 10.3390/math11143069.Peña, D. (2005). Análisis de series temporales. Alianza editorial.Phi, M. (2018), ‘Illustrated guide to lstm’s and gru’s: A step by step explanation’. https://towardsdatascience.com/illustrated-guide-to-lstms-and-gru-s-a-stepby- step-explanation-44e9eb85bf21, Web; accedido el 01-07-2020.Sak, H., Senior, A. y Beaufays, F. (2014). “Long short-term memory recurrent neural network architectures for large scale acoustic modeling”. INTERSPEECH pp. 338–342.T´ellez, C. & Morales, M. (2016). Modelos estad´ısticos lineales. Con aplicaciones en R, Ediciones de la U, Bogot´a.Trifa, A., Sbai, A. & Chaari, W. (2017). ’Enhancing assessment of personalized multi-agent system through convlstm’, Procedia Computer Science 112, 249–259.Tsay, R. S., y Tiao, G. C. (1984). Consistent estimates of autoregressive parameters and extended sample autocorrelation function for stationary and nonstationary arma models. Journal of the American Statistical Association, 79(385), 84-96. doi: 10.1080/01621459.1984.10477068.Tomek, W. y Robinson, K. (2005). Agricultural Product Prices. Cornell University Press.Valencia, M., Yañez, C. y Sanchez, L. (2006).Algoritmo blackpropagation para Redes Neuronales: conceptos y aplicaciones. M´exico.Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N.,Kaiser, L. y Polosukhin, I.. Attention Is All You Need. 2017. arXiv: 1706. 03762.Wagner, R. H. (1982).“A noncooperative solution to a two-person bargaining game”. Unpublished paper.Weaver, R. y W. Natcher,W. (2000). Has market reform exposed farmers to greater price volatility?. In Farm Economics, Cooperative Extension Service, US Department of Agriculture. College Station, PA:Pennsylvania State University.Yang, j., Nguyen, M., San, P., Li, X. y Krishnaswamy, S. (2015). “Deep convolutional neural networks on multichannel time series for human activity recognition”, Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence pp. 3995–4001.Yu, G., Feng, H., Feng, S., Zhao, J., y Xu, J. (2021). Forecasting hand-footand- mouth disease cases using wavelet-based sarima–nnar hybrid model. PLoS one, 16(2), e0246673.Yule, G.U. (1927). On a method of investigating the periodicities of disturbed series, with special reference to Wolfer’s sunspot numbers. Philosophical Transactions of the Royal Society (A), 226, 267-298.Modelos de series de tiempo clasicosAprendizaje automaticoRedes neuronalesModelos hibridosClassic time series modelsMachine LearningNeural NetworkHybrid modelsPublicationLICENSElicense.txtlicense.txttext/plain; charset=utf-815543https://repositorio.unicordoba.edu.co/bitstreams/5e03307b-4551-454b-a9d0-18cbe8d7d929/download73a5432e0b76442b22b026844140d683MD51ORIGINALYEHISON MIRANDA_ISAAC PÉREZ.pdfYEHISON MIRANDA_ISAAC PÉREZ.pdfapplication/pdf5372446https://repositorio.unicordoba.edu.co/bitstreams/7ac5a632-c3ad-4b7f-b9e4-461422a15814/download983c6717d6a19af31f38256497fe92afMD54FROMATO DE AUTORIZACIÓN.pdfFROMATO DE AUTORIZACIÓN.pdfapplication/pdf359524https://repositorio.unicordoba.edu.co/bitstreams/8d6e1f98-6a82-4f94-931e-8d76b9a7a037/download55d62a0adf0d2b3c844be6a6ecad664bMD55TEXTYEHISON MIRANDA_ISAAC PÉREZ.pdf.txtYEHISON MIRANDA_ISAAC PÉREZ.pdf.txtExtracted texttext/plain101873https://repositorio.unicordoba.edu.co/bitstreams/d7cf3872-be8d-4c36-9902-555f044a07ca/downloade02e584c7e92b63bc0fa58144684a50eMD56FROMATO DE AUTORIZACIÓN.pdf.txtFROMATO DE AUTORIZACIÓN.pdf.txtExtracted texttext/plain6011https://repositorio.unicordoba.edu.co/bitstreams/716ed71e-e355-4de3-b9c5-a011a3a1c14f/downloadb90cbcdf51c3553201af6cd3f43f2973MD58THUMBNAILYEHISON MIRANDA_ISAAC PÉREZ.pdf.jpgYEHISON MIRANDA_ISAAC PÉREZ.pdf.jpgGenerated Thumbnailimage/jpeg8568https://repositorio.unicordoba.edu.co/bitstreams/c95632a8-d4ba-4544-9025-a719121a983a/downloadc44c237e66251a20f86888e1e6bf4039MD57FROMATO DE AUTORIZACIÓN.pdf.jpgFROMATO DE AUTORIZACIÓN.pdf.jpgGenerated Thumbnailimage/jpeg14271https://repositorio.unicordoba.edu.co/bitstreams/a3854943-7575-40ad-b06d-9e178dc4da72/download01981055f6e65e53839434d6d0dc67b5MD59ucordoba/8809oai:repositorio.unicordoba.edu.co:ucordoba/88092024-12-12 03:00:30.245https://creativecommons.org/licenses/by-nc-sa/4.0/Copyright Universidad de Córdoba, 2024open.accesshttps://repositorio.unicordoba.edu.coRepositorio Universidad de Córdobabdigital@metabiblioteca.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 |