Concurrent Computing for Accelerating Financial Machine Learning Model Training

  • Thiago S. Araújo UFRGS
  • Cristiano A. Künas UFRGS
  • Dennis G. Balreiras UFRGS
  • Arthur F. Lorenzon UFRGS
  • Philippe O. A. Navaux UFRGS
  • Paulo S. G. de Mattos Neto UFPE


The financial market generates a large volume of data daily, allowing the increasing use of machine learning algorithms in building predictive models for the stock market. In this environment, time is a crucial factor since stock prices change daily, so the training time of models is a critical factor. This paper proposes a method to optimize the overall training time of 5 reinforcement learning algorithms that predict the weights of each stock in a stock portfolio. Experiments were conducted by varying the number of algorithms executed simultaneously. In addition, the computational characteristics of each algorithm were analyzed concerning the use of memory and processing. From the proposed combination of running the algorithms concurrently, it was possible to reduce the total training time by 33% compared to running the algorithms sequentially. Moreover, this execution led to a commendable 15% decrease in energy consumption.

Palavras-chave: Reinforcement learning, Performance and energy consumption, Stock market


B. M. Henrique, V. A. Sobreiro, and H. Kimura, “Literature review: Machine learning techniques applied to financial market prediction,” Expert Systems with Applications, vol. 124, pp. 226–251, 2019. [Online]. Available: [link].

R. Durall, “Asset allocation: From markowitz to deep reinforcement learning,” 2022.

T. G. Fischer, “Reinforcement learning in financial markets - a survey,” FAU Discussion Papers in Economics, Nürnberg, FAU Discussion Papers in Economics 12/2018, 2018. [Online]. Available: [link]

O. Y. Al-Jarrah, P. D. Yoo, S. Muhaidat, G. K. Karagiannidis, and K. Taha, “Efficient machine learning for big data: A review,” Big Data Research, vol. 2, no. 3, pp. 87–93, 2015.

O. Hegazy, O. S. Soliman, and M. A. Salam, “A machine learning model for stock market prediction,” arXiv preprint arXiv:1402.7351, 2014.

I. Parmar, N. Agarwal, S. Saxena, R. Arora, S. Gupta, H. Dhiman, and L. Chouhan, “Stock market prediction using machine learning,” in 2018 first international conference on secure cyber computing and communication (ICSCCC). IEEE, 2018, pp. 574–576.

W. Khan, M. A. Ghazanfar, M. A. Azam, A. Karami, K. H. Alyoubi, and A. S. Alfakeeh, “Stock market prediction using machine learning classifiers and social media, news,” Journal of Ambient Intelligence and Humanized Computing, pp. 1–24, 2020.

M. Vijh, D. Chandola, V. A. Tikkiwal, and A. Kumar, “Stock closing price prediction using machine learning techniques,” Procedia computer science, vol. 167, pp. 599–606, 2020.

B. Hambly, R. Xu, and H. Yang, “Recent advances in reinforcement learning in finance,” Mathematical Finance, vol. 33, no. 3, pp. 437–503, 2023.

H. Yang, X.-Y. Liu, S. Zhong, and A. Walid, “Deep reinforcement learning for automated stock trading: An ensemble strategy,” in Proceedings of the first ACM international conference on AI in finance, 2020, pp. 1–8.

Z. Tianqing, W. Zhou, D. Ye, Z. Cheng, and J. Li, “Resource allocation in iot edge computing via concurrent federated reinforcement learning,” IEEE Internet of Things Journal, vol. 9, no. 2, pp. 1414–1426, 2021.

L. Schuler, S. Jamil, and N. Kühl, “Ai-based resource allocation: Reinforcement learning for adaptive auto-scaling in serverless environments,” in 2021 IEEE/ACM 21st International Symposium on Cluster, Cloud and Internet Computing (CCGrid). IEEE, 2021, pp. 804–811.

C. Shyalika, T. Silva, and A. Karunananda, “Reinforcement learning in dynamic task scheduling: A review,” SN Computer Science, vol. 1, pp. 1–17, 2020.

J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. Klimov, “Proximal policy optimization algorithms,” arXiv preprint arXiv:1707.06347, 2017.

T. P. Lillicrap, J. J. Hunt, A. Pritzel, N. Heess, T. Erez, Y. Tassa, D. Silver, and D. Wierstra, “Continuous control with deep reinforcement learning,” arXiv preprint arXiv:1509.02971, 2015.

T. Haarnoja, A. Zhou, K. Hartikainen, G. Tucker, S. Ha, J. Tan, V. Kumar, H. Zhu, A. Gupta, P. Abbeel et al., “Soft actor-critic algorithms and applications,” arXiv preprint arXiv:1812.05905, 2018.
ARAÚJO, Thiago S.; KÜNAS, Cristiano A.; BALREIRAS, Dennis G.; LORENZON, Arthur F.; NAVAUX, Philippe O. A.; MATTOS NETO, Paulo S. G. de. Concurrent Computing for Accelerating Financial Machine Learning Model Training. In: TRABALHOS EM ANDAMENTO - SIMPÓSIO BRASILEIRO DE ENGENHARIA DE SISTEMAS COMPUTACIONAIS (SBESC), 13. , 2023, Porto Alegre/RS. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2023 . p. 59-62. ISSN 2763-9002. DOI: