dc.contributorVillarreal Navarro, Julio Ernesto
dc.contributorÁbrego Pérez, Adriana Lourdes
dc.contributorVillarreal Daza, Nicolás
dc.creatorMorales Acevedo, Andrés
dc.date.accessioned2022-06-24T21:06:41Z
dc.date.available2022-06-24T21:06:41Z
dc.date.created2022-06-24T21:06:41Z
dc.date.issued2022-06-23
dc.identifierhttp://hdl.handle.net/1992/58281
dc.identifierinstname:Universidad de los Andes
dc.identifierreponame:Repositorio Institucional Séneca
dc.identifierrepourl:https://repositorio.uniandes.edu.co/
dc.description.abstractLa aplicación de técnicas de Machine Learning en finanzas ha generado valor para los agentes que las han implementado (Robust Tech House, 2020). No obstante, las investigaciones en el campo de valoración y compraventa de opciones se han centrado en Machine Learning supervisado y procesamiento de lenguaje natural, llevando a que todavía haya bastante por explorar en la implementación de aprendizaje por refuerzo y aprendizaje profundo (Goodell, Kumar, Lim, & Pattnaik, 2021). La presente investigación se centra en este campo y propone desarrollar un algoritmo de trading de opciones americanas tipo call sobre acciones, utilizando los precios intradía con intervalos de un minuto. El algoritmo desarrollado, dentro de la aplicación del aprendizaje por refuerzo, es de Q-Learning e incluye una red neuronal recurrente con una Gated Recurrent Unit. El resultado demuestra la capacidad del modelo por aprender las condiciones del ambiente, realizar predicciones y generar beneficios por trading hasta alcanzar costos netos de cobertura menores o iguales a cero.
dc.description.abstractMachine Learning techniques in finance have created value for the agents that have implemented them (Robust Tech House, 2020). However, research in the field of option valuation and trading has focused on supervised machine learning and natural language processing, so there is still much to investigate in its application within reinforcement learning and deep learning (Goodell, Kumar, Lim, & Pattnaik, 2021). This study focuses on this field and proposes an algorithm for trading American call stock options using intraday prices at one-minute intervals. The algorithm developed implements Q-Learning, a reinforcement learning methodology, and includes a recurrent neural network with a Gated Recurrent Unit. The results demonstrate the ability of the model to learn the conditions of the environment, make predictions, and generate benefits from trading until the point where it reaches net hedging costs less than or equal to zero.
dc.languagespa
dc.publisherUniversidad de los Andes
dc.publisherMaestría en Ingeniería Industrial
dc.publisherFacultad de Ingeniería
dc.publisherDepartamento de Ingeniería Industrial
dc.relationAziz, S., Dowling, M., Hammami, H., & Piepenbrink, A. (2022). Machine learning in finance: A topic modeling approach. European Financial Management, 744-770.
dc.relationBalazs, H. (Mayo de 2022). Machine Learning and Deep Learning Bootcamp in Python. Obtenido de Udemy: https://www.udemy.com/course/introduction-to-machine-learning-in-python/
dc.relationBarchart. (20 de Mayo de 2022). Most Active Stock Options. Obtenido de https://www.barchart.com/options/most-active/stocks?orderBy=optionsTotalVolume&orderDir=desc
dc.relationBayer, C., Friz, P., & Gatheral, J. (2016). Pricing under rough volatility. Quantitative Finance, 887-904.
dc.relationChung, J., Gulcehre, C., Cho, K., & Bengio, Y. (11 de Diciembre de 2014). Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. Obtenido de Cornell University: https://arxiv.org/abs/1412.3555v1
dc.relationDobilas, S. (21 de Febrero de 2022). GRU Recurrent Neural Networks - A Smart Way to Predict Sequences in Python. Obtenido de Towards Science: https://towardsdatascience.com/gru-recurrent-neural-networks-a-smart-way-to-predict-sequences-in-python-80864e4fe9f6
dc.relationGoodell, J., Kumar, S., Lim, W., & Pattnaik, D. (2021). Artificial intelligence and machine learning in finance: Identifying foundations, themes, and research clusters from bibliometric analysis. Journal of Behavioral and Experimental Finance, 32.
dc.relationGoudenège, L., Molent, A., & Zanette, A. (2020). Machine learning for pricing American options in high-dimensional Markovian and non-Markovian models. Quantitative Finance, 573-591.
dc.relationHalperin, I. (2019). The QLBS Q-Learner goes NuQLear: fitted Q iteration, inverse RL, and option portfolios. Quantitative Finance, 1543-1553.
dc.relationHan, J., & Jentzen, A. (2018). Solving High-DImensional Partial Difference Equations Using Deep Learning. PNAS, 8505-8510.
dc.relationIBM. (17 de Agosto de 2021). El modelo de redes neuronales. Obtenido de SPSS Modeler: https://www.ibm.com/docs/es/spss-modeler/SaaS?topic=networks-neural-model
dc.relationJansen, S. (2018). Hands-On Machine Learning for Algorithmic Trading. Birmingham: Packt Publishing.
dc.relationJian, N., Xu, Y., Li, Z., & Zhao, J. (2022). Copper price movement prediction using recurrent neural networks and ensemble averaging. Soft Comput, https://doi.org/10.1007/s00500-022-07201-w.
dc.relationLi, Y., Ni, P., & Chang, V. (2019). Application of deep reinforcement learning in stock trading strategies and stock forecasting. Computing, 1305-1322.
dc.relationMcDowell, H. (8 de Abril de 2021). Machine learning futures algo trading surges at JP Morgan. Obtenido de The Trade: https://www.thetradenews.com/machine-learning-futures-algo-trading-surges-at-jp-morgan/
dc.relationMcKinsey. (8 de Diciembre de 2021). The state of AI in 2021. Obtenido de AI adoption and impact: https://www.mckinsey.com/business-functions/quantumblack/our-insights/global-survey-the-state-of-ai-in-2021
dc.relationMnih, V., Kavukcuoglu, K., Silver, D., Rusu, A., Veness, J., Bellemare, M., . . . Ostrovski, G. (2015). Human-level control through deep reinforcement. Nature, 529-543.
dc.relationPortafolio. (14 de Abril de 2022). Los detalles de oferta que presentó Elon Musk por el 100 % de Twitter. Obtenido de https://www.portafolio.co/negocios/empresas/elon-musk-presenta-oferta-para-comprar-el-100-de-twitter-564070
dc.relationQuartz. (5 de Mayo de 2015). Artificial intelligence is the next big thing for hedge funds seeking an edge. Obtenido de https://qz.com/389647/artificial-intelligence-is-the-next-big-thing-for-hedge-funds-seeking-an-edge/
dc.relationRebellion. (2022). Our AI - The Future of Machine Learning Financial Planning. Obtenido de Rebellion Research AI Asset Management: https://www.rebellionresearch.com/our-ai
dc.relationRobust Tech House. (22 de Mayo de 2020). List Of Funds Or Trading Firms Using Artificial Intelligence Or Machine Learning. Obtenido de https://robusttechhouse.com/list-of-funds-or-trading-firms-using-artificial-intelligence-or-machine-learning/
dc.relationTabor, P. (Octubre de 2020). Modern Reinforcement Learning: Deep Q Learning in PyTorch. Obtenido de https://www.udemy.com/course/deep-q-learning-from-paper-to-code/
dc.relationTemple, J. (10 de Septiembre de 2014). Introducing Binatix: A Deep Learning Trading Firm That's Already Profitable. Obtenido de Recode: https://www.vox.com/2014/9/10/11630724/introducing-binatix-a-deep-learning-trading-firm-thats-already
dc.relationTorres, J. (2022). Deep Learning. Obtenido de Introducción a la práctica con Keras (primera parte): https://torres.ai/deep-learning-inteligencia-artificial-keras/
dc.relationValencia, C. (2021). Métodos de ensamble- clase de Statistical Learning for Data Analytics. Bogotá: Universidad de los Andes.
dc.relationVan Hasselt, H., Guez, A., & Silver, D. (8 de Diciembre de 2015). Deep Reinforcement Learning with Double Q-learning. Recuperado el 10 de Junio de 2022, de Cornell University: https://arxiv.org/abs/1509.06461
dc.relationVillarreal, J. (2020). Eficiencia de mercado. Bogotá: Universidad de los Andes.
dc.relationWang, T. (2019). Recurrent Neural Network. Obtenido de University of Toronto: https://www.cs.toronto.edu/~tingwuwang/rnn_tutorial.pdf
dc.relationWang, X., Li, J., & Li, J. (2022). A Deep Learning Based Numerical PDE Method for Option Pricing. Computational Economics, 1-16.
dc.relationWang, Z., Schaul, T., Hessel, M., Van Hasselt, H., Lanctot, M., & de Freitas, N. (5 de Abril de 2016). Dueling Network Architectures for Deep Reinforcement Learning. Obtenido de Cornell University: https://arxiv.org/abs/1511.06581
dc.relationWen, W., Yuan, Y., & Yang, J. (2021). Reinforcement Learning for Options Trading. Applied Sciences, 11(23).
dc.relationZhang, J., & Huang, W. (2021). Option hedging using LSTM-RNN: an empirical analysis. Quantitative Finance, 1753-1772.
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 Internacional
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 Internacional
dc.rightshttp://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rightsinfo:eu-repo/semantics/openAccess
dc.rightshttp://purl.org/coar/access_right/c_abf2
dc.titleDesarrollo de un algoritmo, utilizando Machine Learning, para generar estrategias de arbitraje en coberturas de opciones sobre acciones
dc.typeTrabajo de grado - Maestría


Este ítem pertenece a la siguiente institución