Abstract
The stock market is a complex network that consists of individual stocks exhibiting various financial properties and different data distribution. For stock prediction, it is natural to build separate models for each stock but also consider the complex hidden correlation among a set of stocks. We propose a federated multi-task stock predictor with financial graph Laplacian regularization (FMSP-FGL). Specifically, we first introduce a federated multi-task framework with graph Laplacian regularization to fit separate but related stock predictors simultaneously. Then, we investigate the problem of graph Laplacian learning, which represents the association of the dynamic stock. We show that the proposed optimization problem with financial Laplacian constraints captures both the inter-series correlation between each pair of stocks and the relationship within the same stock cluster, which helps improve the predictive performance. Empirical results on two popular stock indexes demonstrate that the proposed method outperforms baseline approaches. To the best of our knowledge, this is the first work to utilize the advantage of graph Laplacian in multi-task learning for financial data to predict multiple stocks in parallel.
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
Similar content being viewed by others
Notes
- 1.
In total, we collect 29 stocks from DJIA, because the stock, DOW, was listed after 2017.
- 2.
Technical indicators: Moving Average Convergence Divergence, Average Directional Movement Index, Awesome Oscillator, Money Flow Index, Upper Bollinger Bands, Lower Bollinger Bands, Chaikin Money Flow, On-balance Volume Mean Range.
References
Gics. https://www.msci.com/our-solutions/indexes/gics. Accessed 7 Oct 2021
Abadir, K.M., Magnus, J.R.: Matrix Algebra, vol. 1. Cambridge University Press, Cambridge (2005)
Boyd, S., Boyd, S.P., Vandenberghe, L.: Convex Optimization. Cambridge University Press, Cambridge (2004)
Boyd, S., Parikh, N., Chu, E.: Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers. Now Publishers Inc., Delft (2011)
Brisimi, T.S., Chen, R., Mela, T., Olshevsky, A., Paschalidis, I.C., Shi, W.: Federated learning of predictive models from federated electronic health records. Int. J. Med. Inform. 112, 59–67 (2018)
Cardoso, J.V.d.M., Palomar, D.P.: Learning undirected graphs in financial markets. arXiv preprint arXiv:2005.09958 (2020)
Cardoso, J.V.d.M., Ying, J., Palomar, D.P.: Algorithms for learning graphs in financial markets. arXiv preprint arXiv:2012.15410 (2020)
Chen, M., Yang, Z., Saad, W., Yin, C., Poor, H.V., Cui, S.: A joint learning and communications framework for federated learning over wireless networks. IEEE Trans. Wirel. Commun. 20(1), 269–283 (2020)
Cont, R.: Empirical properties of asset returns: stylized facts and statistical issues. Quanti. Financ. 1(2), 223 (2001)
Diamond, S., Boyd, S.: CVXPY: a Python-embedded modeling language for convex optimization. J. Mach. Learn. Res. 17(83), 1–5 (2016)
Dinh, C.T., Vu, T.T., Tran, N.H., Dao, M.N., Zhang, H.: Fedu: a unified framework for federated multi-task learning with Laplacian regularization. arXiv preprint arXiv:2102.07148 (2021)
Dong, X., Thanou, D., Frossard, P., Vandergheynst, P.: Learning Laplacian matrix in smooth graph signal representations. IEEE Trans. Sig. Process. 64(23), 6160–6173 (2016)
Fan, K.: On a theorem of Weyl concerning eigenvalues of linear transformations I. Proc. Natl. Acad. Sci. U.S.A. 35(11), 652 (1949)
He, J., Khushi, M., Tran, N.H., Liu, T.: Robust dual recurrent neural networks for financial time series prediction. In: Proceedings of the 2021 SIAM International Conference on Data Mining (SDM), pp. 747–755. SIAM (2021)
Hou, K.: Industry information diffusion and the lead-lag effect in stock returns. Rev. Financ. Stud. 20(4), 1113–1138 (2007)
Kalofolias, V.: How to learn a graph from smooth signals. In: Artificial Intelligence and Statistics, pp. 920–929. PMLR (2016)
Li, C., Song, D., Tao, D.: Multi-task recurrent neural networks and higher-order Markov random fields for stock price movement prediction: Multi-task RNN and higer-order MRFs for stock price classification. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1141–1151 (2019)
Mantegna, R.N.: Hierarchical structure in financial markets. Eur. Phys. J. B Condens. Matter Compl. Syst. 11(1), 193–197 (1999)
Markowitz, H.M.: Portfolio Selection. Yale University Press, London (1968)
Marti, G., Nielsen, F., Bińkowski, M., Donnat, P.: A review of two decades of correlations, hierarchies, networks and clustering in financial markets. Prog. Inf. Geom. 245–274 (2021)
Nie, F., Wang, X., Jordan, M.I., Huang, H.: The constrained Laplacian rank algorithm for graph-based clustering. In: Thirtieth AAAI Conference on Artificial Intelligence (2016)
Oellermann, O.R., Schwenk, A.J.: The Laplacian spectrum of graphs (1991)
Paszke, A., et al.: Automatic differentiation in pytorch (2017)
Qin, Y., Song, D., Chen, H., Cheng, W., Jiang, G., Cottrell, G.: A dual-stage attention-based recurrent neural network for time series prediction. arXiv preprint arXiv:1704.02971 (2017)
Smith, V., Chiang, C.K., Sanjabi, M., Talwalkar, A.: Federated multi-task learning. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 4427–4437. Curran Associates Inc. (2017)
Tuck, J., Barratt, S., Boyd, S.: A distributed method for fitting Laplacian regularized stratified models. arXiv preprint arXiv:1904.12017 (2019)
Yoo, J., Soun, Y., Park, Y.c., Kang, U.: Accurate multivariate stock movement prediction via data-axis transformer with multi-level contexts. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 2037–2045 (2021)
Zhang, Y., Yeung, D.Y.: A convex formulation for learning task relationships in multi-task learning. arXiv preprint arXiv:1203.3536 (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
He, J., Tran, N.H., Khushi, M. (2022). Stock Predictor with Graph Laplacian-Based Multi-task Learning. In: Groen, D., de Mulatier, C., Paszynski, M., Krzhizhanovskaya, V.V., Dongarra, J.J., Sloot, P.M.A. (eds) Computational Science – ICCS 2022. ICCS 2022. Lecture Notes in Computer Science, vol 13350. Springer, Cham. https://doi.org/10.1007/978-3-031-08751-6_39
Download citation
DOI: https://doi.org/10.1007/978-3-031-08751-6_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-08750-9
Online ISBN: 978-3-031-08751-6
eBook Packages: Computer ScienceComputer Science (R0)