Machine learning para arbitraje financiero en el mercado de renta variable colombiano

El desarrollo y la tecnificación de los mercados de capitales en los últimos años ha derivado en una competencia entre los actores del mismo por la búsqueda de oportunidades de inversión mediante el uso de herramientas computacionales veloces, potentes y sofisticadas. El hallazgo de patrones en algu...

Full description

Autores:
Tipo de recurso:
Fecha de publicación:
2022
Institución:
Universidad del Rosario
Repositorio:
Repositorio EdocUR - U. Rosario
Idioma:
spa
OAI Identifier:
oai:repository.urosario.edu.co:10336/38196
Acceso en línea:
https://doi.org/10.48713/10336_38196
https://repository.urosario.edu.co/handle/10336/38196
Palabra clave:
Arbitraje
Trading de alta frecuencia
Mercados capitales
Herramientas computacionales
Inversiones, innovaciones tecnológicas
Inteligencia artificial
Trading algorítmico
Mercado de renta variable colombiano
Arbitrage
High frequency trading
Capital markets
Investments, technological innovations
Artificial intelligence
Computing tools
Algorithmic trading
Colombian equity market
Rights
License
Attribution-NonCommercial-ShareAlike 4.0 International
id EDOCUR2_c5de959999dd962b2d124bdf8101f1cf
oai_identifier_str oai:repository.urosario.edu.co:10336/38196
network_acronym_str EDOCUR2
network_name_str Repositorio EdocUR - U. Rosario
repository_id_str
dc.title.none.fl_str_mv Machine learning para arbitraje financiero en el mercado de renta variable colombiano
dc.title.TranslatedTitle.none.fl_str_mv Machine learning for financial arbitrage in the colombian stock market
title Machine learning para arbitraje financiero en el mercado de renta variable colombiano
spellingShingle Machine learning para arbitraje financiero en el mercado de renta variable colombiano
Arbitraje
Trading de alta frecuencia
Mercados capitales
Herramientas computacionales
Inversiones, innovaciones tecnológicas
Inteligencia artificial
Trading algorítmico
Mercado de renta variable colombiano
Arbitrage
High frequency trading
Capital markets
Investments, technological innovations
Artificial intelligence
Computing tools
Algorithmic trading
Colombian equity market
title_short Machine learning para arbitraje financiero en el mercado de renta variable colombiano
title_full Machine learning para arbitraje financiero en el mercado de renta variable colombiano
title_fullStr Machine learning para arbitraje financiero en el mercado de renta variable colombiano
title_full_unstemmed Machine learning para arbitraje financiero en el mercado de renta variable colombiano
title_sort Machine learning para arbitraje financiero en el mercado de renta variable colombiano
dc.contributor.advisor.none.fl_str_mv Caicedo, Alexander
Andrade Lotero, Édgar José
dc.subject.none.fl_str_mv Arbitraje
Trading de alta frecuencia
Mercados capitales
Herramientas computacionales
Inversiones, innovaciones tecnológicas
Inteligencia artificial
Trading algorítmico
Mercado de renta variable colombiano
topic Arbitraje
Trading de alta frecuencia
Mercados capitales
Herramientas computacionales
Inversiones, innovaciones tecnológicas
Inteligencia artificial
Trading algorítmico
Mercado de renta variable colombiano
Arbitrage
High frequency trading
Capital markets
Investments, technological innovations
Artificial intelligence
Computing tools
Algorithmic trading
Colombian equity market
dc.subject.keyword.none.fl_str_mv Arbitrage
High frequency trading
Capital markets
Investments, technological innovations
Artificial intelligence
Computing tools
Algorithmic trading
Colombian equity market
description El desarrollo y la tecnificación de los mercados de capitales en los últimos años ha derivado en una competencia entre los actores del mismo por la búsqueda de oportunidades de inversión mediante el uso de herramientas computacionales veloces, potentes y sofisticadas. El hallazgo de patrones en algunas oportunidades de inversión cuya duración es de fracciones de segundo pero que pueden ocurrir un sin número de veces en el término de un día, multiplica las oportunidades de aquellos inversionistas que se encuentran bien equipados para explotarlas a su favor. En el presente trabajo, mostraremos como se pueden aplicar algunas técnicas de inteligencia artificial para construir estrategias rentables de trading algorítmico en el mercado de renta variable colombiano. Construiremos varios modelos de Machine y Deep Learnig capaces de predecir con precisión aceptable, algunas oportunidades de inversión que se presentan en ventanas cortas de tiempo. Mostraremos con detalle cuáles son las capacidades predictivas de los modelos desarrollados y los retornos esperados
publishDate 2022
dc.date.created.none.fl_str_mv 2022-12-26
dc.date.accessioned.none.fl_str_mv 2023-03-08T13:15:57Z
dc.date.available.none.fl_str_mv 2023-03-08T13:15:57Z
dc.type.none.fl_str_mv bachelorThesis
dc.type.coar.fl_str_mv http://purl.org/coar/resource_type/c_7a1f
dc.type.document.none.fl_str_mv Trabajo de grado
dc.type.spa.none.fl_str_mv Trabajo de grado
dc.identifier.doi.none.fl_str_mv https://doi.org/10.48713/10336_38196
dc.identifier.uri.none.fl_str_mv https://repository.urosario.edu.co/handle/10336/38196
url https://doi.org/10.48713/10336_38196
https://repository.urosario.edu.co/handle/10336/38196
dc.language.iso.none.fl_str_mv spa
language spa
dc.rights.*.fl_str_mv Attribution-NonCommercial-ShareAlike 4.0 International
dc.rights.coar.fl_str_mv http://purl.org/coar/access_right/c_abf2
dc.rights.acceso.none.fl_str_mv Abierto (Texto Completo)
dc.rights.uri.*.fl_str_mv http://creativecommons.org/licenses/by-nc-sa/4.0/
rights_invalid_str_mv Attribution-NonCommercial-ShareAlike 4.0 International
Abierto (Texto Completo)
http://creativecommons.org/licenses/by-nc-sa/4.0/
http://purl.org/coar/access_right/c_abf2
dc.format.extent.none.fl_str_mv 53 pp
dc.format.mimetype.none.fl_str_mv application/pdf
dc.publisher.spa.fl_str_mv Universidad del Rosario
dc.publisher.department.spa.fl_str_mv Escuela de Ingeniería, Ciencia y Tecnología
dc.publisher.program.spa.fl_str_mv Maestría en Matemáticas Aplicadas y Ciencias de la Computación
institution Universidad del Rosario
dc.source.bibliographicCitation.none.fl_str_mv Dominik Ro ̈sch. The impact of arbitrage on market liquidity. Journal of Financial Economics, 142, 05 2021.
Jim Fischer. Modern portfolio theory and the efficient markets hypothesis: How well did they serve canada’s baby-boom generation? 10 2019.
Eugene Fama. Efficient capital markets: A review of theory and empirical work. Journal of Finance, 25:383–417, 1970.
J. M. Samuels. Inefficient capital markets and their implications. 1981.
ShireenTang,ShijieHuang,ElizabethBowman,CarstenMurawski,andPeter Bossaerts. The efficient markets hypothesis does not hold when securities valuation is computationally hard. SSRN Electronic Journal, 01 2017.
Jonathan B. Berk. A critique of the efficient market hypothesis. 2008.
Veliota Drakopoulou. A review of fundamental and technical stock analysis techniques. Journal of Stock Forex Trading, 05, 01 2016.
Mohamed Masry. The impact of technical analysis on stock returns in an emerging capital markets (ecm’s) country: Theoretical and empirical study. International Journal of Economics and Finance, 9:91, 02 2017.
SophieEmerson,Ruair ́ıKennedy,LukeO’Shea,andJohnR.O’Brien.Trends and applications of machine learning in quantitative finance. Machine Learn- ing eJournal, 2019.
Benoit B. Mandelbrot. The variation of certain speculative prices, pages 371–418. Springer New York, New York, NY, 1997.
S. Patterson. Dark Pools: The Rise of the Machine Traders and the Rigging of the U.S. Stock Market. Crown, 2013.
S. Patterson. The Quants: How a New Breed of Math Whizzes Conquered Wall Street and Nearly Destroyed It. Crown, 2010.
Zhe Huang and Franck Martin. Optimal pairs trading strategies in a cointe- gration framework. July 2017. working paper or preprint.
Sayad Baronyan, I. Ilkay Boduroglu, and EMRAH S ̧ENER. Investigation of stochastic pairs trading strategies under different volatility regimes. The Manchester School, 78:114 – 134, 09 2010.
K. J. Hong and S. Satchell. Time series momentum trading strategy and autocorrelation amplification. Quantitative Finance, 15(9):1471–1487, 2015.
Andy Lin and Illya Barziy. Pairs trading based on renko and kagi models, Oct 2021.
JohnMoodyandMatthewSaffell.Learningtotradeviadirectreinforcement. IEEE transactions on neural networks / a publication of the IEEE Neural Networks Council, 12:875–89, 07 2001.
Riccardo Rosati, Luca Romeo, Carlos Alfaro Goday, Tullio Menga, and Emanuele Frontoni. Machine learning in capital markets: Decision support system for outcome analysis. IEEE Access, 8:109080–109091, 2020.
James J. Choi, David Laibson, Brigitte C. Madrian, and Andrew Met- rick. Reinforcement Learning and Savings Behavior. Journal of Finance, 64(6):2515–2534, December 2009.
GAndrewKarolyiandStijnVanNieuwerburgh.NewMethodsfortheCross- Section of Returns. The Review of Financial Studies, 33(5):1879–1890, 02 2020.
Paul Yoo, Maria H. Kim, and T. Jan. Machine learning techniques and use of event information for stock market prediction: A survey and evalua- tion. International Conference on Computational Intelligence for Modelling, Control and Automation and International Conference on Intelligent Agents, Web Technologies and Internet Commerce (CIMCA-IAWTIC’06), 2:835–841, 2005.
Patrick Jaquart, David Dann, and Christof Weinhardt. Short-term bitcoin market prediction via machine learning. The Journal of Finance and Data Science, 7:45–66, 2021.
Adriano Koshiyama, Nick Firoozye, and Philip Treleaven. Algorithms in future capital markets: A survey on ai, ml and associated algorithms in capital markets. In Proceedings of the First ACM International Conference on AI in Finance, ICAIF ’20, New York, NY, USA, 2021. Association for Computing Machinery.
Nicolas Huck. Large data sets and machine learning: Applications to statis- tical arbitrage. European Journal of Operational Research, 278(1):330–342, 2019.
Baoqiang Zhan, Shu Zhang, Helen Du, and Xiaoguang Yang. Exploring statistical arbitrage opportunities using machine learning strategy. Computa- tional Economics, 60, 11 2021.
GeorgeEPBoxandGwilymMJenkins.Somecommentsonapaperbychat- field and prothero and on a review by kendall. Journal of the Royal Statistical Society. Series A (General), 136(3):337–352, 1973.
dc.source.instname.none.fl_str_mv instname:Universidad del Rosario
dc.source.reponame.spa.fl_str_mv reponame:Repositorio Institucional EdocUR
bitstream.url.fl_str_mv https://repository.urosario.edu.co/bitstreams/bca363cb-7b4f-461c-9ead-48b0cb2ffdd5/download
https://repository.urosario.edu.co/bitstreams/d1de3286-20e2-4af2-800a-04a44102bb8a/download
https://repository.urosario.edu.co/bitstreams/488261f1-259d-43a8-a456-d2c32125f449/download
https://repository.urosario.edu.co/bitstreams/d4044cb2-a655-4b10-ba9e-054b682345b0/download
https://repository.urosario.edu.co/bitstreams/41b308dc-111a-4d78-87bc-5330cc1b28b8/download
bitstream.checksum.fl_str_mv a7a1fb2714b53936280bdf8df3b461e7
b2825df9f458e9d5d96ee8b7cd74fde6
5643bfd9bcf29d560eeec56d584edaa9
ab3d6b754e405a7dd60dcf41aa36733a
d63f18f27faf5bf5a02770057c5a79de
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
MD5
MD5
repository.name.fl_str_mv Repositorio institucional EdocUR
repository.mail.fl_str_mv edocur@urosario.edu.co
_version_ 1808390709382742016
spelling Caicedo, Alexanderd5d8b83a-b05d-45f6-a683-03e0c7090331-1Andrade Lotero, Édgar José95ab7599-4981-49d0-a5f4-110463e87e54Ramírez, Daniel EduardoSegura, Jaime AugustoMagíster en Matemáticas Aplicadas y Ciencias de la ComputaciónFull time17f0ca20-f157-4fea-998a-98bafcdba00f-166491e47-b9fa-4fe5-9e71-09b41626bf7f-12023-03-08T13:15:57Z2023-03-08T13:15:57Z2022-12-26El desarrollo y la tecnificación de los mercados de capitales en los últimos años ha derivado en una competencia entre los actores del mismo por la búsqueda de oportunidades de inversión mediante el uso de herramientas computacionales veloces, potentes y sofisticadas. El hallazgo de patrones en algunas oportunidades de inversión cuya duración es de fracciones de segundo pero que pueden ocurrir un sin número de veces en el término de un día, multiplica las oportunidades de aquellos inversionistas que se encuentran bien equipados para explotarlas a su favor. En el presente trabajo, mostraremos como se pueden aplicar algunas técnicas de inteligencia artificial para construir estrategias rentables de trading algorítmico en el mercado de renta variable colombiano. Construiremos varios modelos de Machine y Deep Learnig capaces de predecir con precisión aceptable, algunas oportunidades de inversión que se presentan en ventanas cortas de tiempo. Mostraremos con detalle cuáles son las capacidades predictivas de los modelos desarrollados y los retornos esperadosThe development and modernization of capital markets in recent years has led to competition among its players in search of investment opportunities through the use of fast, powerful, and sophisticated computational tools. Finding patterns in some investment opportunities that last for fractions of a second but can occur countless times in the span of a day multiplies the opportunities for those investors who are well equipped to exploit them. in his favor. In this paper, we will show how some artificial intelligence techniques can be applied to build profitable algorithmic trading strategies in the Colombian equity market. We will build several Machine and Deep Learning models capable of predicting with acceptable precision, some investment opportunities that arise in short windows of time. We will show in detail what are the predictive capabilities of the developed models and the expected returns53 ppapplication/pdfhttps://doi.org/10.48713/10336_38196 https://repository.urosario.edu.co/handle/10336/38196spaUniversidad del RosarioEscuela de Ingeniería, Ciencia y TecnologíaMaestría en Matemáticas Aplicadas y Ciencias de la ComputaciónAttribution-NonCommercial-ShareAlike 4.0 InternationalAbierto (Texto Completo)http://creativecommons.org/licenses/by-nc-sa/4.0/http://purl.org/coar/access_right/c_abf2Dominik Ro ̈sch. The impact of arbitrage on market liquidity. Journal of Financial Economics, 142, 05 2021.Jim Fischer. Modern portfolio theory and the efficient markets hypothesis: How well did they serve canada’s baby-boom generation? 10 2019.Eugene Fama. Efficient capital markets: A review of theory and empirical work. Journal of Finance, 25:383–417, 1970.J. M. Samuels. Inefficient capital markets and their implications. 1981.ShireenTang,ShijieHuang,ElizabethBowman,CarstenMurawski,andPeter Bossaerts. The efficient markets hypothesis does not hold when securities valuation is computationally hard. SSRN Electronic Journal, 01 2017.Jonathan B. Berk. A critique of the efficient market hypothesis. 2008.Veliota Drakopoulou. A review of fundamental and technical stock analysis techniques. Journal of Stock Forex Trading, 05, 01 2016.Mohamed Masry. The impact of technical analysis on stock returns in an emerging capital markets (ecm’s) country: Theoretical and empirical study. International Journal of Economics and Finance, 9:91, 02 2017.SophieEmerson,Ruair ́ıKennedy,LukeO’Shea,andJohnR.O’Brien.Trends and applications of machine learning in quantitative finance. Machine Learn- ing eJournal, 2019.Benoit B. Mandelbrot. The variation of certain speculative prices, pages 371–418. Springer New York, New York, NY, 1997.S. Patterson. Dark Pools: The Rise of the Machine Traders and the Rigging of the U.S. Stock Market. Crown, 2013.S. Patterson. The Quants: How a New Breed of Math Whizzes Conquered Wall Street and Nearly Destroyed It. Crown, 2010.Zhe Huang and Franck Martin. Optimal pairs trading strategies in a cointe- gration framework. July 2017. working paper or preprint.Sayad Baronyan, I. Ilkay Boduroglu, and EMRAH S ̧ENER. Investigation of stochastic pairs trading strategies under different volatility regimes. The Manchester School, 78:114 – 134, 09 2010.K. J. Hong and S. Satchell. Time series momentum trading strategy and autocorrelation amplification. Quantitative Finance, 15(9):1471–1487, 2015.Andy Lin and Illya Barziy. Pairs trading based on renko and kagi models, Oct 2021.JohnMoodyandMatthewSaffell.Learningtotradeviadirectreinforcement. IEEE transactions on neural networks / a publication of the IEEE Neural Networks Council, 12:875–89, 07 2001.Riccardo Rosati, Luca Romeo, Carlos Alfaro Goday, Tullio Menga, and Emanuele Frontoni. Machine learning in capital markets: Decision support system for outcome analysis. IEEE Access, 8:109080–109091, 2020.James J. Choi, David Laibson, Brigitte C. Madrian, and Andrew Met- rick. Reinforcement Learning and Savings Behavior. Journal of Finance, 64(6):2515–2534, December 2009.GAndrewKarolyiandStijnVanNieuwerburgh.NewMethodsfortheCross- Section of Returns. The Review of Financial Studies, 33(5):1879–1890, 02 2020.Paul Yoo, Maria H. Kim, and T. Jan. Machine learning techniques and use of event information for stock market prediction: A survey and evalua- tion. International Conference on Computational Intelligence for Modelling, Control and Automation and International Conference on Intelligent Agents, Web Technologies and Internet Commerce (CIMCA-IAWTIC’06), 2:835–841, 2005.Patrick Jaquart, David Dann, and Christof Weinhardt. Short-term bitcoin market prediction via machine learning. The Journal of Finance and Data Science, 7:45–66, 2021.Adriano Koshiyama, Nick Firoozye, and Philip Treleaven. Algorithms in future capital markets: A survey on ai, ml and associated algorithms in capital markets. In Proceedings of the First ACM International Conference on AI in Finance, ICAIF ’20, New York, NY, USA, 2021. Association for Computing Machinery.Nicolas Huck. Large data sets and machine learning: Applications to statis- tical arbitrage. European Journal of Operational Research, 278(1):330–342, 2019.Baoqiang Zhan, Shu Zhang, Helen Du, and Xiaoguang Yang. Exploring statistical arbitrage opportunities using machine learning strategy. Computa- tional Economics, 60, 11 2021.GeorgeEPBoxandGwilymMJenkins.Somecommentsonapaperbychat- field and prothero and on a review by kendall. Journal of the Royal Statistical Society. Series A (General), 136(3):337–352, 1973.instname:Universidad del Rosarioreponame:Repositorio Institucional EdocURArbitrajeTrading de alta frecuenciaMercados capitalesHerramientas computacionalesInversiones, innovaciones tecnológicasInteligencia artificialTrading algorítmicoMercado de renta variable colombianoArbitrageHigh frequency tradingCapital marketsInvestments, technological innovationsArtificial intelligenceComputing toolsAlgorithmic tradingColombian equity marketMachine learning para arbitraje financiero en el mercado de renta variable colombianoMachine learning for financial arbitrage in the colombian stock marketbachelorThesisTrabajo de gradoTrabajo de gradohttp://purl.org/coar/resource_type/c_7a1fEscuela de AdministraciónORIGINALMachine-learning-para-arbitraje-financiero.pdfMachine-learning-para-arbitraje-financiero.pdfapplication/pdf1561857https://repository.urosario.edu.co/bitstreams/bca363cb-7b4f-461c-9ead-48b0cb2ffdd5/downloada7a1fb2714b53936280bdf8df3b461e7MD51LICENSElicense.txtlicense.txttext/plain1483https://repository.urosario.edu.co/bitstreams/d1de3286-20e2-4af2-800a-04a44102bb8a/downloadb2825df9f458e9d5d96ee8b7cd74fde6MD52CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-81160https://repository.urosario.edu.co/bitstreams/488261f1-259d-43a8-a456-d2c32125f449/download5643bfd9bcf29d560eeec56d584edaa9MD53TEXTMachine-learning-para-arbitraje-financiero.pdf.txtMachine-learning-para-arbitraje-financiero.pdf.txtExtracted texttext/plain70703https://repository.urosario.edu.co/bitstreams/d4044cb2-a655-4b10-ba9e-054b682345b0/downloadab3d6b754e405a7dd60dcf41aa36733aMD54THUMBNAILMachine-learning-para-arbitraje-financiero.pdf.jpgMachine-learning-para-arbitraje-financiero.pdf.jpgGenerated Thumbnailimage/jpeg2792https://repository.urosario.edu.co/bitstreams/41b308dc-111a-4d78-87bc-5330cc1b28b8/downloadd63f18f27faf5bf5a02770057c5a79deMD5510336/38196oai:repository.urosario.edu.co:10336/381962024-08-23 09:25:51.009http://creativecommons.org/licenses/by-nc-sa/4.0/Attribution-NonCommercial-ShareAlike 4.0 Internationalhttps://repository.urosario.edu.coRepositorio institucional EdocURedocur@urosario.edu.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

Publicaciones similares