Skip to main content
SpringerLink
Log in

Combining dimensionality reduction methods with neural networks for realized volatility forecasting

  • Original Research
  • Published:
Annals of Operations Research Aims and scope Submit manuscript

Abstract

The application of artificial neural networks to finance has recently received a great deal of attention from both investors and researchers, particularly as a forecasting tool. However, when dealing with a large number of predictors, these methods may overfit the data and provide poor out-of-sample forecasts. Our paper addresses this issue by employing two different approaches to predict realized volatility. On the one hand, we use a two-step procedure where several dimensionality reduction methods, such as Bayesian Model Averaging (BMA), Principal Component Analysis (PCA), and Least Absolute Shrinkage and Selection Operator (Lasso), are employed in the initial step to reduce dimensionality. The reduced samples are then combined with artificial neutral networks. On the other hand, we implement two single-step regularized neural networks that can shrink the input weights to zero and effectively handle high-dimensional data. Our findings on the volatility of different stock asset prices indicate that the reduced models outperform the compared models without regularization in terms of predictive accuracy.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  • Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., & Zheng, X. (2015). TensorFlow: Large-scale machine learning on heterogeneous systems. Retrieved from https://www.tensorflow.org/ (Software available from tensorflow.org)

  • Abdi, H., & Williams, L. J. (2010). Principal component analysis. Wiley Interdisciplinary Reviews: Computational Statistics, 2, 433–459.

    Article  Google Scholar 

  • Amengual, D., & Xiu, D. (2018). Resolution of policy uncertainty and sudden declines in volatility. Journal of Econometrics, 203(2), 297–315.

    Article  Google Scholar 

  • Andersen, T. G., Bollerslev, T., Diebold, F. X., & Ebens, H. (2001a). The distribution of realized stock return volatility. Journal of Financial Economics, 61, 43–76.

  • Andersen, T. G., Bollerslev, T., Diebold, F. X., & Labys, P. (2001b). The distribution of realized exchange rate volatility. Journal of the American Statistical Association, 96, 42–55.

  • Andersen, T. G., Bollerslev, T., Diebold, F. X., & Labys, P. (2003a). Modeling and forecasting realized volatility. Econometrica, 71(2), 579–625.

  • Andersen, T. G., Bollerslev, T., Diebold, F. X., & Labys, P. (2003b). Modeling and forecasting realized volatility. Econometrica, 71(3), 579–625.

  • Ang, A., & Bekaert, G. (2007). Stock return predictability: Is it there? The Review of Financial Studies, 20, 651–707.

    Article  Google Scholar 

  • Baker, S. R., Bloom, N., & Davis, S. J. (2016). Measuring economic policy uncertainty. The Quarterly Journal of Economics, 131, 1593–1636.

    Article  Google Scholar 

  • Balcilar, M., Ozdemir, Z. A., & Ozdemir, H. (2021). Dynamic return and volatility spillovers among S &P 500, crude oil, and gold. International Journal of Finance & Economics, 26(1), 153–170. https://doi.org/10.1002/ijfe.1782

    Article  Google Scholar 

  • Barbieri, M. M., & Berger, J. O. (2004). Optimal predictive model selection. The Annals of Statistics, 32(3), 870–897. https://doi.org/10.1214/009053604000000238

    Article  Google Scholar 

  • Bergmeir, C., & Beńýtez, J. M. (2012). Neural networks in R using the Stuttgart neural network simulator: RSNNS. Journal of Statistical Software, 46(7), 1–26.

    Article  Google Scholar 

  • Black, F. (1976). Noise. Journal of Finance, 41, 529–543.

    Article  Google Scholar 

  • Bucci, A. (2020a). Cholesky—ANN models for predicting multivariate realized volatility. Journal of Forecasting, 39(6), 865–876.

  • Bucci, A. (2020b). Realized volatility forecasting with neural networks. Journal of Financial Econometrics, 18, 502–531.

  • Chang, C.-L., McAleer, M., & Tansuchat, R. (2010). Analyzing and forecasting volatility spillovers, asymmetries and hedging in major oil markets. Energy Economics, 32(6), 1445–1455.

    Article  Google Scholar 

  • Christensen, K., Siggaard, M., & Veliyev, B. (2022). A machine learning approach to volatility forecasting. Journal of Financial Econometrics. https://doi.org/10.1093/jjfinec/nbac020

    Article  Google Scholar 

  • Christiansen, C., Schmeling, M., & Schrimpf, A. (2012). A comprehensive look at financial volatility prediction by economic variables. Journal of Applied Econometrics, 27, 956–977.

    Article  Google Scholar 

  • Corsi, F. (2009). A simple approximate long-memory model of realized volatility. Journal of Financial Econometrics, 7(2), 174–196.

    Article  Google Scholar 

  • Elman, J. L. (1990). Finding structure in time. Cognitive Science, 14(2), 179–211.

    Article  Google Scholar 

  • Fama, E. F., & French, K. R. (1993). Common risk factors in the returns on stocks and bonds. Journal of Financial Economics, 33(1), 3–56.

    Article  Google Scholar 

  • Foroni, C., Guérin, P., & Marcellino, M. (2018). Using low frequency information for predicting high frequency variables. International Journal of Forecasting, 34(4), 774–787.

    Article  Google Scholar 

  • Fritsch, S., Guenther, F., Wright, M.N. (2019). neuralnet: Training of neural networks [Computer software manual]. Retrieved from https://CRAN.Rproject.org/package=neuralnet (R package version 1.44.2)

  • Garcia-Donato, G., & Forte, A. (2018). Bayesian Testing, Variable Selection and Model Averaging in Linear Models using R with BayesVarSel. The R Journal, 10(1), 155–174. https://doi.org/10.32614/RJ-2018-021

    Article  Google Scholar 

  • Giacomini, R., & White, H. (2006). Tests of conditional predictive ability. Econometrica, 74(6), 1545–1578.

    Article  Google Scholar 

  • Hajizadeh, E., Seifi, A., Zarandi, M. F., & Turksen, I. (2012). A hybrid modeling approach for forecasting the volatility of S &P 500 index return. Expert Systems with Applications, 39, 431–436.

    Article  Google Scholar 

  • Hansen, B. E. (2016). The risk of James–Stein and lasso shrinkage. Econometric Reviews, 35(8–10), 1456–1470.

    Article  Google Scholar 

  • Hansen, P. R., & Lunde, A. (2005). A forecast comparison of volatility models: Does anything beat a GARCH(1,1)? Journal of Applied Econometrics, 20(7), 873–889.

    Article  Google Scholar 

  • Hansen, P. R., Lunde, A., & Nason, J. M. (2011). The model confidence set. Econometrica, 79(2), 453–497.

    Article  Google Scholar 

  • Hastie, T., Tibshirani, R., & Friedman, J. (2001). The elements of statistical learning. New York: Springer.

    Book  Google Scholar 

  • Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780.

    Article  Google Scholar 

  • Huang, X., & Tauchen, G. (2005). The relative contribution of jumps to total price variation. Journal of Financial Econometrics, 3(4), 456–499.

    Article  Google Scholar 

  • Jolliffe, I. T., & Cadima, J. (2016). Principal component analysis: A review and recent developments. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 374(2065), 20150202.

    Article  Google Scholar 

  • Jordan, M.I. (1997). Serial order: A parallel distributed processing approach. In Advances in psychology (Vol. 121, pp. 471–495). Elsevier.

  • Jurado, K., Ludvigson, S. C., & Ng, S. (2015). Measuring uncertainty. American Economic Review, 105(3), 1177–1216.

    Article  Google Scholar 

  • Lemhadri, I., Ruan, F., Abraham, L., & Tibshirani, R. (2022). LassoNet: A neural network with feature sparsity. Journal of Machine Learning Research, 22, 1–29.

    Google Scholar 

  • Linting, M., van Os, B. J., & Meulman, J. J. (2011). Statistical significance of the contribution of variables to the PCA solution: An alternative permutation strategy. Psychometrika, 76(3), 440–460. https://doi.org/10.1007/s11336-011-9216-6

    Article  Google Scholar 

  • Liu, C., Zhao, Z., & Wen, G. (2019). Adaptive neural network control with optimal number of hidden nodes for trajectory tracking of robot manipulators. Neurocomputing, 350, 136–145.

    Article  Google Scholar 

  • Liu, L., & Zhang, T. (2015). Economic policy uncertainty and stock market volatility. Finance Research Letters, 15, 99–105.

    Article  Google Scholar 

  • Liu, Z. H., Meng, X. D., Wei, H. L., Chen, L., Lu, Z. H., Wang, Bi-Liangand., & Chen, L. (2021). A regularized LSTM method for predicting remaining useful life of rolling bearings. International Journal of Automation and Computing, 18(4), 581–593. https://doi.org/10.1007/s11633-020-1276-6

    Article  Google Scholar 

  • Maciel, L., Gomide, F., & Ballini, R. (2016). Evolving fuzzy-GARCH approach for financial volatility modeling and forecasting. Computational Economics, 48, 379–398.

    Article  Google Scholar 

  • Maheu, J. M., & McCurdy, T. H. (2002). Nonlinear features of realized volatility. Review of Economics and Statistics, 84, 668–681.

    Article  Google Scholar 

  • Marzo, M., & Zagaglia, P. (2010). Volatility forecasting for crude oil futures. Applied Economics Letters, 17(16), 1587–1599.

    Article  Google Scholar 

  • McAleer, M., & Medeiros, M. (2008a). A multiple regime smooth transition Heterogeneous Autoregressive model for long memory and asymmetries. Journal of Econometrics, 147, 104–119.

  • McAleer, M., & Medeiros, M. C. (2008b). Realized volatility: A review. Econometric Reviews, 27, 10–45.

  • Montgomery, J. M., & Nyhan, B. (2010). Bayesian model averaging: Theoretical developments and practical applications. Political Analysis, 18, 245–270.

    Article  Google Scholar 

  • Nagel, S. (2012). Evaporating liquidity. The Review of Financial Studies, 25(7), 2005–2039. https://doi.org/10.1093/rfs/hhs066

    Article  Google Scholar 

  • Nelson, D. B. (1990). Stationarity and persistence in the GARCH (1,1) model. Econometric Theory, 6, 318–334.

    Article  Google Scholar 

  • Patton, A. J. (2011). Volatility forecast comparison using imperfect volatility proxies. Journal of Econometrics, 160(1), 246–256.

    Article  Google Scholar 

  • Paye, B. S. (2012). ‘Déjà vol’: Predictive regressions for aggregate stock market volatility using macroeconomic variables. Journal of Financial Economics, 106(3), 527–546.

    Article  Google Scholar 

  • Rossi, E., & Santucci de Magistris, P. (2014). Estimation of long memory in integrated variance. Econometric Reviews, 33(7), 785–814.

    Article  Google Scholar 

  • Sadorsky, P. (2006). Modeling and forecasting petroleum futures volatility. Energy Economics, 28(4), 467–488.

    Article  Google Scholar 

  • Shlens, J. (2014). A tutorial on principal component analysis. arXiv:1404.1100 .

  • Stinchcombe, M., & White, H. (1992). Using feedforward networks to distinguish multivariate populations. In Proceedings of the international joint conference on neural networks.

  • Verleysen, M., & François, D. (2005). The curse of dimensionality in data mining and time series prediction. J. Cabestany, A. Prieto, & F. Sandoval (Eds.), Computational intelligence and bioinspired systems (pp. 758–770). Berlin: Springer.

  • Vo, M. T. (2009). Regime-switching stochastic volatility: Evidence from the crude oil market. Energy Economics, 31(5), 779–788.

    Article  Google Scholar 

  • Wanas, N., Auda, G., Kamel, M.S., & Karray, F. (1998). On the optimal number of hidden nodes in a neural network. In Conference proceedings. IEEE Canadian conference on electrical and computer engineering (cat. no.98th8341) (Vol. 2, pp. 918–921). Retrieved from https://doi.org/10.1109/CCECE.1998.685648

  • Welch, I., & Goyal, A. (2008). A comprehensive look at the empirical performance of equity premium prediction. The Review of Financial Studies, 21(4), 1455–1508.

    Article  Google Scholar 

Download references

Funding

Zhi Liu’s research is supported by NSFC (No. 11971507), and The Science and Technology Development Fund (FDCT) of Macau (No. 0041/2021/ITP and 0079/2020/A2).

Author information

Authors and Affiliations

  1. Department of Economics and Law, University of Macerata, Via Crescimbeni, 62100, Macerata, Italy

    Andrea Bucci

  2. School of Mathematics and Statistics, Nanjing University of Information Science and Technology, 219 Ningliu Road, Pukou District, Nanjing, 211544, China

    Lidan He

  3. Faculty of Science and Technology, University of Macau, Avenida de Universidade, Taipa, Macau, China

    Zhi Liu

Authors
  1. Andrea Bucci
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lidan He
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhi Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Andrea Bucci.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendices

List of predictors

See Table 11.

Table 11 Description of the predictors
Full size table
Table 12 Average computational time (in seconds) across assets for each combination of architecture, number of nodes and dimensionality reduction technique
Full size table

Computational time

We conducted the model training using a laptop equipped with an Intel® Core™i7-11800 H 2.3GHz processor and 16 GB RAM. The FNNs were trained using the R package neuralnet (Fritsch et al. 2019), while ENNs and JNNs were trained using the R package RSNNS (Bergmeir and Beńýtez 2012). The LSTM was trained using the Python packages tensorflow (Abadi et al. 2015) and keras. Lassonet was trained using the Python code supplied in Lemhadri et al. (2022), and E-LSTM was trained using the Python code supplied in Liu et al. (2021). The average computational time across all assets for all replications is reported in Table 12.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Bucci, A., He, L. & Liu, Z. Combining dimensionality reduction methods with neural networks for realized volatility forecasting. Ann Oper Res (2023). https://doi.org/10.1007/s10479-023-05544-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s10479-023-05544-7

Keywords

JEL Classification

Search

Navigation