Skip to main content
SpringerLink
Log in

Towards an efficient machine learning model for financial time series forecasting

  • Data analytics and machine learning
  • Published:
Soft Computing Aims and scope Submit manuscript

Abstract

Financial time series forecasting is a challenging problem owing to the high degree of randomness and absence of residuals in time series data. Existing machine learning solutions normally do not perform well on such data. In this study, we propose an efficient machine learning model for financial time series forecasting through carefully designed feature extraction, elimination, and selection strategies. We leverage a binary particle swarm optimization algorithm to select the appropriate features and propose new evaluation metrics, i.e. mean weighted square error and mean weighted square ratio, for better performance assessment in handling financial time series data. Both indicators ascertain that our proposed model is effective, which outperforms several existing methods in benchmark studies.

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

Data availability

Data are publicly available.

References

  • Aguilar-Rivera R, Valenzuela-Rendón M, Rodríguez-Ortiz J (2015) Genetic algorithms and Darwinian approaches in financial applications: a survey. Expert Syst Appl 42(21):7684–7697

    Google Scholar 

  • Alghamdi T, Mostafi S, Abdelkader G et al (2022) A comparative study on traffic modeling techniques for predicting and simulating traffic behavior. Future Internet 14(10):294

    Google Scholar 

  • Alhnaity B, Abbod M (2020) A new hybrid financial time series prediction model. Eng Appl Artif Intell 95(103):873

    Google Scholar 

  • Amini MH, Kargarian A, Karabasoglu O (2016) Arima-based decoupled time series forecasting of electric vehicle charging demand for stochastic power system operation. Electr Power Syst Res 140:378–390

    Google Scholar 

  • Assareh E, Behrang M, Assari M et al (2010) Application of PSO (particle swarm optimization) and GA (genetic algorithm) techniques on demand estimation of oil in Iran. Energy 35(12):5223–5229

    Google Scholar 

  • Barak S, Sadegh SS (2016) Forecasting energy consumption using ensemble ARIMA–ANFIS hybrid algorithm. Int J Electr Power Energy Syst 82:92–104

    Google Scholar 

  • Bashir F, Wei HL (2018) Handling missing data in multivariate time series using a vector autoregressive model-imputation (VAR-IM) algorithm. Neurocomputing 276:23–30

    Google Scholar 

  • Box GE, Jenkins GM, Reinsel GC et al (2015) Time series analysis: forecasting and control. Wiley

    MATH  Google Scholar 

  • Büyükşahin ÜÇ, Ertekin Ş (2019) Improving forecasting accuracy of time series data using a new ARIMA–ANN hybrid method and empirical mode decomposition. Neurocomputing 361:151–163

    Google Scholar 

  • Carriero A, Kapetanios G, Marcellino M (2009) Forecasting exchange rates with a large Bayesian VAR. Int J Forecast 25(2):400–417

    Google Scholar 

  • Chen T, Guestrin C (2016) Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp 785–794

  • Chen T, He T, Benesty M et al (2015) Xgboost: extreme gradient boosting. R package version 04-2 1(4):1–4

  • Chortareas G, Jiang Y, Nankervis JC (2011) Forecasting exchange rate volatility using high-frequency data: is the euro different? Int J Forecast 27(4):1089–1107

    Google Scholar 

  • Christ M, Braun N, Neuffer J et al (2018) Time series feature extraction on basis of scalable hypothesis tests (tsfresh-a python package). Neurocomputing 307:72–77

    Google Scholar 

  • Deshmukh SS, Paramasivam R et al (2016) Forecasting of milk production in India with ARIMA and VAR time series models. Asian J Dairy Food Res 35(1):17–22

    Google Scholar 

  • Devi AS, Maragatham G, Boopathi K et al (2020) Hourly day-ahead wind power forecasting with the EEMD–CSO–LSTM–EFG deep learning technique. Soft Comput 24(16):12391–12411

    Google Scholar 

  • EOSIO (2022) Home–eosio blockchain software & services. https://eos.io/

  • Gandomi AH, Yang XS, Alavi AH (2013) Cuckoo search algorithm: a metaheuristic approach to solve structural optimization problems. Eng Comput 29(1):17–35

    Google Scholar 

  • Gupta D, Pratama M, Ma Z et al (2019) Financial time series forecasting using twin support vector regression. PloS ONE 14(3):e0211-402

    Google Scholar 

  • Henrique BM, Sobreiro VA, Kimura H (2018) Stock price prediction using support vector regression on daily and up to the minute prices. J Financ Data Sci 4(3):183–201

    Google Scholar 

  • Henrique BM, Sobreiro VA, Kimura H (2019) Literature review: machine learning techniques applied to financial market prediction. Expert Syst Appl 124:226–251

    Google Scholar 

  • Hewage P, Trovati M, Pereira E et al (2021) Deep learning-based effective fine-grained weather forecasting model. Pattern Anal Appl 24(1):343–366

    Google Scholar 

  • Jiang W, Zhang L (2018) Geospatial data to images: a deep-learning framework for traffic forecasting. Tsinghua Sci Technol 24(1):52–64

    Google Scholar 

  • Johnstone C, Sulungu ED (2021) Application of neural network in prediction of temperature: a review. Neural Comput Appl 33(18):11487–11498

    Google Scholar 

  • Joseph NL (2001) Model specification and forecasting foreign exchange rates with vector autoregressions. J Forecast 20(7):451–484

    Google Scholar 

  • Karevan Z, Suykens JA (2020) Transductive LSTM for time-series prediction: An application to weather forecasting. Neural Netw 125:1–9

    Google Scholar 

  • Kelany O, Aly S, Ismail MA (2020) Deep learning model for financial time series prediction. In: 2020 14th International conference on innovations in information technology (IIT). IEEE, pp 120–125

  • Kennedy J, Eberhart RC (1997) A discrete binary version of the particle swarm algorithm. In: 1997 IEEE international conference on systems, man, and cybernetics. Computational cybernetics and simulation, IEEE, pp 4104–4108

  • Lai G, Chang W, Yang Y et al (2018) Modeling long- and short-term temporal patterns with deep neural networks. In: Collins-Thompson K, Mei Q, Davison BD et al (eds) The 41st international ACM SIGIR conference on research & development in information retrieval, SIGIR 2018, Ann Arbor, MI, USA, July 08–12, 2018. ACM, pp 95–104, https://doi.org/10.1145/3209978.3210006

  • Lee K, Jeong Y, Joo S et al (2022) Outliers in financial time series data: outliers, margin debt, and economic recession. Mach Learn Appl 10(100):420

    Google Scholar 

  • Liu C, Hoi SCH, Zhao P et al (2016) Online ARIMA algorithms for time series prediction. In: Schuurmans D, Wellman MP (eds) Proceedings of the thirtieth AAAI conference on artificial intelligence, February 12–17, 2016, Phoenix, Arizona, USA. AAAI Press, pp 1867–1873. http://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/view/12135

  • Liu J, Li Y (2020) Study on environment-concerned short-term load forecasting model for wind power based on feature extraction and tree regression. J Clean Prod 264(121):505

    Google Scholar 

  • Liu M, Luo K, Zhang J et al (2021) A stock selection algorithm hybridizing grey wolf optimizer and support vector regression. Expert Syst Appl 179(115):078

    Google Scholar 

  • Lu CJ, Lee TS, Chiu CC (2009) Financial time series forecasting using independent component analysis and support vector regression. Dec Support Syst 47(2):115–125

    Google Scholar 

  • Ma K, Pang X, Pang H et al (2022) A novel method for favorable zone prediction of conventional hydrocarbon accumulations based on rusboosted tree machine learning algorithm. Appl Energy 326(119):983

    Google Scholar 

  • Maleki M, Wraith D, Mahmoudi MR et al (2020) Asymmetric heavy-tailed vector auto-regressive processes with application to financial data. J Stat Comput Simul 90(2):324–340

    MathSciNet  MATH  Google Scholar 

  • McCrae M, Lin YX, Pavlik D et al (2002) Can cointegration-based forecasting outperform univariate models? an application to Asian exchange rates. J Forecast 21(5):355–380

    Google Scholar 

  • Moosa IA, Vaz JJ (2016) Cointegration, error correction and exchange rate forecasting. J Int Financ Mark Inst Money 44:21–34

    Google Scholar 

  • Munkhdalai L, Li M, Theera-Umpon N et al (2020) Var-gru: a hybrid model for multivariate financial time series prediction. In: Asian conference on intelligent information and database systems. Springer, pp 322–332

  • Ngueyep R, Serban N (2015) Large-vector autoregression for multilayer spatially correlated time series. Technometrics 57(2):207–216

    MathSciNet  Google Scholar 

  • Ouma YO, Moalafhi DB, Anderson G et al (2022) Dam water level prediction using vector autoregression, random forest regression and MLP–ANN models based on land-use and climate factors. Sustainability 14(22):14,934

    Google Scholar 

  • Qiu H, Xu S, Han F et al (2015) Robust estimation of transition matrices in high dimensional heavy-tailed vector autoregressive processes. In: International conference on machine learning. PMLR, pp 1843–1851

  • Ristanoski G, Liu W, Bailey J (2013) Time series forecasting using distribution enhanced linear regression. In: Pacific-Asia conference on knowledge discovery and data mining. Springer, pp 484–495

  • Safikhani A, Shojaie A (2022) Joint structural break detection and parameter estimation in high-dimensional nonstationary VAR models. J Am Stat Assoc 117(537):251–264

    MathSciNet  MATH  Google Scholar 

  • Sezer OB, Gudelek MU, Ozbayoglu AM (2020) Financial time series forecasting with deep learning: a systematic literature review: 2005–2019. Appl Soft Comput 90(106):181

    Google Scholar 

  • Shih SY, Sun FK, Hy Lee (2019) Temporal pattern attention for multivariate time series forecasting. Mach Learn 108(8):1421–1441

    MathSciNet  MATH  Google Scholar 

  • Singh S, Mohapatra A et al (2019) Repeated wavelet transform based ARIMA model for very short-term wind speed forecasting. Renew Energy 136:758–768

    Google Scholar 

  • Sun Q, Zhou WX, Fan J (2020) Adaptive Huber regression. J Am Stat Assoc 115(529):254–265

    MathSciNet  MATH  Google Scholar 

  • Sun S, Wang S, Wei Y (2019) A new multiscale decomposition ensemble approach for forecasting exchange rates. Econ Model 81:49–58

    Google Scholar 

  • Tang C, Shi Y (2021) Forecasting high-dimensional financial functional time series: An application to constituent stocks in Dow Jones index. J Risk Financ Manag 14(8):343

    MathSciNet  Google Scholar 

  • Taveeapiradeecharoen P, Chamnongthai K, Aunsri N (2019) Bayesian compressed vector autoregression for financial time-series analysis and forecasting. IEEE Access 7(16):777–16,786

    Google Scholar 

  • Taylor SJ, Letham B (2018) Forecasting at scale. Am Stat 72(1):37–45

    MathSciNet  MATH  Google Scholar 

  • Tseng FM, Tzeng GH, Yu HC et al (2001) Fuzzy ARIMA model for forecasting the foreign exchange market. Fuzzy Sets Syst 118(1):9–19

  • Vankadara LC, Faller PM, Hardt M et al (2022) Causal forecasting: generalization bounds for autoregressive models. In: Uncertainty in artificial intelligence. PMLR, pp 2002–2012

  • Volkova S, Ayton E, Porterfield K et al (2017) Forecasting influenza-like illness dynamics for military populations using neural networks and social media. PloS ONE 12(12):e0188-941

    Google Scholar 

  • Wang H, Liu Y, Wang D et al (2022) Multi-layer echo state network with nonlinear vector autoregression reservoir for time series prediction. In: International conference on neural computing for advanced applications. Springer, pp 489–502

  • West KD, Cho D (1995) The predictive ability of several models of exchange rate volatility. J Econom 69(2):367–391

    Google Scholar 

  • Xu D, Zhang Q, Ding Y et al (2022) Application of a hybrid ARIMA–LSTM model based on the SPEI for drought forecasting. Environ Sci Pollut Res 29(3):4128–4144

    Google Scholar 

  • Yu B, Yin H, Zhu Z (2018) Spatio–temporal graph convolutional networks: a deep learning framework for traffic forecasting. In: Lang J (ed) Proceedings of the twenty-seventh international joint conference on artificial intelligence, IJCAI 2018, July 13–19, 2018, Stockholm, Sweden. ijcai.org, pp 3634–3640. https://doi.org/10.24963/ijcai.2018/505

  • Yu R, Li Y, Shahabi C et al (2017) Deep learning: a generic approach for extreme condition traffic forecasting. In: Chawla NV, Wang W (eds) Proceedings of the 2017 SIAM international conference on data mining, Houston, Texas, USA, April 27–29, 2017. SIAM, pp 777–785. https://doi.org/10.1137/1.9781611974973.87

  • Zhong X, Enke D (2019) Predicting the daily return direction of the stock market using hybrid machine learning algorithms. Financ Innov 5(1):1–20

    Google Scholar 

Download references

Acknowledgements

The authors express their sincere thanks to the referees whose valuable comments helped to improve the presentation.

Funding

Not applicable.

Author information

Authors and Affiliations

  1. Department of Mathematics, Indian Institute of Technology Guwahati, Guwahati, 781039, India

    Arun Kumar, Tanya Chauhan & Srinivasan Natesan

  2. Computational Biology and Bioinformatics Laboratory, Department of Integrative Biotechnology, College of Biotechnology and Bioengineering, Sungkyunkwan University, Suwon, Gyeonggi-do, 16419, Republic of Korea

    Nhat Truong Pham

  3. Institute for Intelligent Systems Research and Innovation, Deakin University, Waurn Ponds, VIC, 3216, Australia

    Ngoc Duy Nguyen & Chee Peng Lim

Authors
  1. Arun Kumar
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tanya Chauhan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Srinivasan Natesan
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Nhat Truong Pham
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Ngoc Duy Nguyen
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Chee Peng Lim
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Srinivasan Natesan.

Ethics declarations

Conflict of interest

There is no conflict of interest.

Additional information

Publisher's Note

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

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

Kumar, A., Chauhan, T., Natesan, S. et al. Towards an efficient machine learning model for financial time series forecasting. Soft Comput 27, 11329–11339 (2023). https://doi.org/10.1007/s00500-023-08676-x

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00500-023-08676-x

Keywords

Search

Navigation