Aplicación de autoencoders y autoencoders variacionales al sparse index tracking del S&P100
Application of Autoencoders and Variational Autoencoders to Sparse Index Tracking of the S&P100
Barra lateral del artículo
PDF
FLIP
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-CompartirIgual 4.0.
Contenido principal del artículo
Resumen
Este artículo explora el uso de autoencoders (AE) y autoencoders variacionales (VAE) para abordar el problema de sparse index tracking aplicado al índice S&P100. Utilizando datos diarios de 2019 a 2023, se construyeron portafolios de seguimiento disperso con 5, 10, 15 y 20 activos, seleccionados mediante un enfoque de información comunal. Los resultados muestran que los VAE superan a los AE en términos de precisión y generalización, logrando un menor empirical tracking error en todos los portafolios. Este estudio destaca el potencial de los VAE como herramientas efectivas para replicar índices financieros bajo restricciones de cardinalidad, aunque no se consideraron costos de transacción ni otras fricciones del mercado.
Palabras clave
Descargas
Detalles del artículo
Referencias (VER)
Benidis, K., Feng, Y. y Palomar, D. (2018). Sparse portfolios for high-dimensional financial index tracking, IEEE Trans. Signal Processing, 66(1), 155-170. 10.1109/TSP.2017.2762286. DOI: https://doi.org/10.1109/TSP.2017.2762286
Bogle, J. C. (1999). Common sense on mutual funds: New imperatives for the intelligent investor. John Wiley & Sons.
Bontempi, G., Ben Taieb, S. y Lecue, F. (2013). Machine learning strategies for time series forecasting. European Journal of Operational Research, 234(2), 361-370.
Coleman, T. F., Li, Y. y Henniger, J. (2006). Minimizing tracking error while restricting the number of assets. Journal of Risk, 8(4), 33. DOI: https://doi.org/10.21314/JOR.2006.134
Fama, E. F. (1970). Efficient capital markets: A review of theory and empirical work. The Journal of Finance, 25(2), 383-417. DOI: https://doi.org/10.1111/j.1540-6261.1970.tb00518.x
Feng, Y. y Palomar, D. P. (2016). A signal processing perspective on financial engineering. Foundations and Trends® in Signal Processing, 9(1-2), 1-231. DOI: https://doi.org/10.1561/2000000072
Heaton, J. B., Polson, N. G. y Witte, J. H. (2017). Deep learning for finance: Deep portfolios. Applied Stochastic Models in Business and Industry, 33(1), 3-12. https://doi.org/10.1002/asmb.2209. DOI: https://doi.org/10.1002/asmb.2209
Hinton, G. E. y Salakhutdinov, R. (2006). Reducing the dimensionality of data with neural networks, Science, 313(5786), 504507. https://doi.org/10.1126/science.1127647 DOI: https://doi.org/10.1126/science.1127647
Kim, S. y Kim, S. (2019). Index tracking through deep latent representation learning. Quantitative Finance, 20(4), 639-652. https://doi.org/10.1080/14697688.2019.1683599 DOI: https://doi.org/10.1080/14697688.2019.1683599
Kingma, D. P. y Welling, M. (2019). An introduction to variational autoencoders. Foundations and Trends® in Machine Learning, 12(4), 307-392. DOI: https://doi.org/10.1561/2200000056
Malkiel, B. G. (2003). The efficient market hypothesis and its critics. Journal of Economic Perspectives, 17(1), 59-82. DOI: https://doi.org/10.1257/089533003321164958
Mutunge, P. y Haugland, D. (2018). Minimizing the tracking error of cardinality constrained portfolios. Computers & Operations Research, 90, 33-41. https://doi.org/10.1016/j.cor.2017.09.002 DOI: https://doi.org/10.1016/j.cor.2017.09.002
Ni, L. y Zhang, J. (2013). Portfolio optimization for index investing based on self-organizing neural network. In KIm, Y. H. t Yarlagadda, P., editor, Sensors, Measurement and intelligent DOI: https://doi.org/10.4028/www.scientific.net/AMM.303-306.1595
Materials (vol. 303-306, pp. 1595-1598). Applied Mechanics and Materials.
Ouyang, H., Zhang, X., Yan, H. (2019). Index tracking based on deep neural network. Cognitive Systems Research, 57, 107-114. https://doi.org/10.1016/j.cogsys.2018.10.022 DOI: https://doi.org/10.1016/j.cogsys.2018.10.022
Shu, L., Shi, F., Tian, G. (2020). High-dimensional index tracking based on the adaptive elastic net. Quantitative Finance, 20(9), 1513-1530. https://doi.org/10.1080/14697688.2020.1737328. DOI: https://doi.org/10.1080/14697688.2020.1737328
Silva, J. C. S. y de Almeida Filho, A. T. (2024). A systematic literature review on solution approaches for the index tracking problem. IMA Journal of Management Mathematics, 35(2), 163-196. DOI: https://doi.org/10.1093/imaman/dpad007
Strub, O. y Baumann, P. (2018). Optimal construction and rebalancing of index-tracking portfolios. European Journal of Operational Research, 264(1), 370-387. DOI: https://doi.org/10.1016/j.ejor.2017.06.055
Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y. y Manzagol, P. A. (2008). Extracting and composing robust features with denoising autoencoders. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(8), 1439-1451.
Vincent, P., Lajoie, I., Bengio, Y. y Manzagol, P. A. (2010). Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. Journal of Machine Learning Research, 11, 3371-3408.
Wang, Y. J., Wu, L. y Wu, L. (2024). An integrative extraction approach for index tracking
portfolio construction and forecasting under a deep learning framework. The Journal of Supercomputing, 80, 2047-2066. https://doi.org/10.1007/s11227-023-05538-z. DOI: https://doi.org/10.1007/s11227-023-05538-z
Zhang, C., Liang, S., Lyu, F. y Fang, L. (2020). Stock-Index Tracking Optimization Using Auto-Encoders. Frontiers in Physic. 8, 388. https://doi.org/10.3389/fphy.2020.00388 DOI: https://doi.org/10.3389/fphy.2020.00388
Citado por
