Abstract
In this paper we propose an alternative machine learning forecasting technique for the canonical problem of predicting expected stock returns. The final goal is enhancing the financial performance of the investment product, which in our case refers to a portfolio of equities. We adopt a combination of algorithms, capable of hand-ling high-level abstraction, to study short- and long-term patterns emerging from the analysis of financial factors and market signals. The core of the model adopted to perform the prediction is composed of two independent entities, analyzing short-term dynamics and capturing long-term trends respectively. This adjustment helps us improve the predictive ability of the model in a dynamic environment, where high volatility and noise are intrinsic features. Lastly, we employ an ensemble algorithm that performs an intelligent weighting of each agent’s output. This method allows us to identify the best stocks in terms of performance and to successfully implement quarter-long hold strategies that outperform the selected universe’s equities return benchmark.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Note that when constructing the training set and target set, you incur two phenomena: missing data and noisy data. To overcome the problem of missing data, we apply the method suggested by Beaver et al. [7]. At the same time, we adopt the approach proposed by Steege et al. [8] to handle the noisy data.
References
Bender, J., et al.: Foundations of Factor Investing. MSCI Index Research (2013)
Welch, I., Goyal, A.: A comprehensive look at the empirical performance of equity premium prediction. Rev. Financ. Stud. 21, 1455–1508 (2008)
Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1995)
Eldan, R., Shamir, O.: The power of depth for feedforward neural networks. In: Feldman, V., Rakhlin, A., Shamir, O. (eds.) 29th Annual Conference on Learning Theory, Proceedings of Machine Learning Research, vol. 49, pp. 907–940 (2016)
Bishop, C.M.: Feed-forward network functions. In: Pattern Recognition and Machine Learning, pp. 226–231 (2016)
Fama, E.F., French, K.R.: A five-factor asset pricing model. J. Financ. Econ. 116(1), 1–22 (2015)
Beaver, W.H., et al.: Delisting returns and their effect on accounting-based market anomalies. SSRN Electron. J. (2006)
Steege, F.-F., et al.: Effects of noise-reduction on neural function approximation. In: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (2012)
Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Netw. 2, 359–366 (1989)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Carlei, V., Terzi, S., Giordani, F., Adamo, G. (2021). Portfolio Management via Empirical Asset Pricing Powered by Machine Learning. In: Bucciarelli, E., Chen, SH., Corchado, J.M., Parra D., J. (eds) Decision Economics: Minds, Machines, and their Society. DECON 2020. Studies in Computational Intelligence, vol 990. Springer, Cham. https://doi.org/10.1007/978-3-030-75583-6_12
Download citation
DOI: https://doi.org/10.1007/978-3-030-75583-6_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-75582-9
Online ISBN: 978-3-030-75583-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)