Skip to main content
SpringerLink
Log in

Best output prediction in OECD railways using DEA in conjunction with machine learning algorithms

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

Abstract

Efficiency measurement plays an increasingly important role in the regulation and management of railway organizations. Despite its proven usefulness in efficiency measurement, data envelopment analysis (DEA) lacks predictive capability. In order to benefit from their learning and mapping capabilities, machine learning (ML) algorithms have been used as a complementary method to DEA, recently. However, the majority of the existing ML-DEA studies focused on efficiency estimation while disregarding the prediction of DEA projected inputs/outputs toward better performance. This study proposes a novel framework using the adaptive neuro-fuzzy inference system (ANFIS) and the support vector machines (SVM) models in conjunction with the context-dependent DEA model to predict efficiency scores and the best input/output levels for 37 railway companies of OECD countries. Despite drawing on a small sample size, the proposed DEA-ANFIS and DEA-SVM models successfully predicted the efficiency scores and the best output levels of the organizations via approximating the efficient frontiers.

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

  • Asmild, M., Holvad, T., Hougaard, J. L., & Kronborg, D. (2009). Railway reforms: Do they influence operating efficiency? Transportation, 36, 617–638.

    Google Scholar 

  • Athanassopoulos, A. D., & Curram, S. P. (1996). A comparison of data envelopment analysis and artificial neural networks as tools for assessing. The Journal of the Operational Research Society, 47(8), 1000–1016.

    Google Scholar 

  • Azadeh, A., Saberi, M., Omar, S. M., Hussain, O. K., & Saberi, Z. (2013). A neuro-fuzzy-multivariate algorithm for accurate gas consumption estimation in South America with noisy inputs. International Journal of Electrical Power & Energy Systems., 46, 315–325.

    Google Scholar 

  • Barros, C. P., & Wanke, P. (2015). An analysis of African airlines efficiency with two-stage TOPSIS and neural networks. Journal of Air Transport Management, 44, 90–102.

    Google Scholar 

  • Bishop, C. M. (2006). Pattern recognition and machine learning. Springer, ISBN 978–0–387–31073–2.

  • Caves, D. W., Christensen, L. R., & Swanson, J. A. (1981). Economic performance in regulated and unregulated environments: A comparison of U.S. and Canadian railroads. Quarterly Journal of Economics, 96(4), 560–581.

    Google Scholar 

  • Charnes, A., Cooper, W. W., & Rhodes, E. (1978). Measuring the efficiency of decision making units. European Journal of Operational Research, 2(6), 429–444.

    Google Scholar 

  • Chen, Y., Morita, H., & Zhu, J. (2005). Context-dependent DEA with an application to Tokyo public libraries. International Journal of Information Technology & Decision Making., 4(3), 385–394.

    Google Scholar 

  • Chen, Z., Matousek, R., & Wanke, P. (2018). Chinese bank efficiency during the global financial crisis: A combined approach using satisficing DEA and Support Vector Machines. The North American Journal of Economics and Finance., 43, 71–86.

    Google Scholar 

  • Coelli, T., & Perelman, S. (1999). A comparison of parametric and non-parametric distance functions: With application to European railways. European Journal of Operational Research, 117, 326–339.

    Google Scholar 

  • Cortes, C., & Vapnik, V. N. (1995). Support-vector networks. Machine Learning, 20(3), 273–297.

    Google Scholar 

  • Davies, A. J., & Kochhar, A. K. (2002). Manufacturing best practice and performance studies: A critique. International Journal of Operations & Production Management, 22(3), 289–305.

    Google Scholar 

  • Emrouznejad, A., & Yang, G. L. (2018). A survey and analysis of the first 40 years of scholarly literature in DEA: 1978–2016. Socio-Economic Planning Sciences, 61, 4–8.

    Google Scholar 

  • Fatimah, S., & Mahmudah, U. (2017). Two-stage data envelopment analysis (DEA) for measuring the efficiency of elementary schools in Indonesia. International Journal of Environmental & Science Education, 12(8), 1971–1987.

    Google Scholar 

  • Growitsch, C., & Wetzel, H. (2009). Testing for economies of scope in European railways an efficiency analysis. Journal of Transport Economics and Policy, 43(1), 1–24.

    Google Scholar 

  • Güneri, A. F., Ertay, T., & Yücel, A. (2011). An approach based on ANFIS input selection and modeling for supplier selection problem. Expert Systems with Applications, 38, 14907–14917.

    Google Scholar 

  • Hilmola, O. P. (2007). European railway freight transportation and adaptation to demand decline. International Journal of Productivity and Performance Management., 56, 205–225.

    Google Scholar 

  • International Quality Study. (1993). Best practices report-an analysis of management practices that impact performance. American Quality Foundation and Ernst & Young.

    Google Scholar 

  • Izadikhah, M., & Saen, R. Z. (2020). Ranking sustainable suppliers by context-dependent data envelopment analysis. Annals of Operations Research, 293, 607–637.

    Google Scholar 

  • James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An introduction to statistical learning (Vol. 112). Springer.

    Google Scholar 

  • Jang, J. S. (1993). ANFIS: Adaptive-network-based fuzzy inference system. IEEE Transactions on Systems Man and Cybernetics, 23, 665–685.

    Google Scholar 

  • Jauhar, S. K., Raj, P. V. R. P., Kamble, S., Gupta, S., & Belhadi, A. (2022). A deep learning-based approach for performance assessment and prediction: A case study of pulp and paper industries. Annals of Operations Research. https://doi.org/10.1007/s10479-022-04528-3

    Article  Google Scholar 

  • Kabasakal, A., Kutlar, A., & Sarikaya, M. (2013). Efficiency determinations of the worldwide railway companies via DEA and contributions of the outputs to the efficiency and TFP by panel regression. Central European Journal of Operations Research, 23(1), 69–88.

    Google Scholar 

  • Kanal, L. N., & Lemmer, J. F. (2014) Uncertainty in artificial intelligence (Vol. 4). Elsevier, eBook ISBN: 9781483296524.

  • Karaboğa, D., & Kaya, E. (2019). Adaptive network based fuzzy inference system (ANFIS) training approaches: A comprehensive survey. Artificial Intelligence Review, 52, 2263–2293.

    Google Scholar 

  • Khaldi, R., El Afia, A., & Chiheb, R. (2019). Performance prediction of pharmaceutical suppliers: comparative study between DEA-ANFIS-PSO and DEA-ANFIS-GA. International Journal of Computer Applications in Technology, 60(4), 317–325.

    Google Scholar 

  • Kouziokas, G. N. (2020). SVM kernel based on particle swarm optimized vector and Bayesian optimized SVM in atmospheric particulate matter forecasting. Applied Soft Computing, 93, 106410.

    Google Scholar 

  • Kwon, H. B., & Lee, J. (2015). Two-stage production modeling of large U.S. banks: A DEA-neural network approach. Expert Systems with Applications, 42(19), 6758–6766.

    Google Scholar 

  • Kwon, H. B. (2017). Exploring the predictive potential of artificial neural networks in conjunction with DEA in railroad performance modeling. International Journal of Production Economics, 183, 159–170.

    Google Scholar 

  • Lan, L. W., & Lin, E. T. J. (2005). Measuring railway performance with adjustment of environmental effects, data noise and slacks. Transportmetrica, 1(2), 161–189.

    Google Scholar 

  • Le, Y., Oka, M., & Kato, H. (2022). Efficiencies of the urban railway lines incorporating financial performance and in-vehicle congestion in the Tokyo Metropolitan Area. Transport Policy., 116, 343–354.

    Google Scholar 

  • Lerida-Navarro, C., Nombela, G., & Tranchez-Martin, J. M. (2019). European railways: Liberalization and productive efficiency. Transport Policy, 83, 57–67.

    Google Scholar 

  • Liang, Y., Hu, S., Guo, W., & Tang, H. (2022). Abrasive tool wear prediction based on an improved hybrid difference grey wolf algorithm for optimizing SVM. Measurement, 187, 110247.

    Google Scholar 

  • Liu, L., Wang, Q., Wang, J., & Liu, M. (2016). A rolling grey model optimized by particle swarm optimization in economic prediction. Computational Intelligence, 32(3), 391–419.

    Google Scholar 

  • Liu, M., Cao, Z., Zhang, J., Wang, L., Huang, C., & Luo, X. (2020). Short-term wind speed forecasting based on the Jaya-SVM model. Electrical Power and Energy Systems, 121, 106056.

    Google Scholar 

  • Modhej, D., Sanei, M., Shoja, N., & Hosseinzadeh, L. F. (2017). Integrating inverse data envelopment analysis and neural network to preserve relative efficiency values. Journal of Intelligent & Fuzzy Systems, 32(6), 4047–4058.

    Google Scholar 

  • OECD 2022. Purchasing power parities (PPP) (indicator). https://doi.org/10.1787/1290ee5a-en (Accessed on 22 March 2022).

  • Oum, T. H., Waters, W. G., & Yu, C. (1999). A survey of productivity and efficiency measurement in rail transport. Journal of Transport Economics and Policy, 33(1), 9–42.

    Google Scholar 

  • Oum, T. H., & Yu, C. (1994). Economic efficiency of railways and implications for public policy: A comparative study of the OECD countries’ railways. Journal of Transport Economics and Policy, 28(2), 121–138.

    Google Scholar 

  • Pendharkar, P. C. (2005). Data envelopment analysis-based approach for data preprocessing. IEEE Transactions on Knowledge and Data Engineering, 17(10), 1379–1388.

    Google Scholar 

  • Pendharkar, P. C., & Rodger, C. A. (2003). Technical efficiency-based selection of learning cases to improve forecasting accuracy of neural networks under monotonicity assumption. Decision Support Systems., 36, 117–136.

    Google Scholar 

  • Poitier, K., & Cho, S. (2011). Estimation of true efficient frontier of organisational performance using data envelopment analysis and support vector machine learning. International Journal of Information and Decision Sciences., 3(2), 148–172.

    Google Scholar 

  • Puri, N.J., & Seita, G. (2023). Performance prediction of DMUs using integrated DEA-SVR approach with imprecise data: application on Indian banks. Soft Computing, 27, 5325–5355.

  • Rajab, S., & Sharma, V. (2018). A review on the applications of neuro-fuzzy systems in business. Artificial Intelligence Review, 49(4), 481–510.

    Google Scholar 

  • Ramón, N., Ruiz, J. L., & Sirvent, I. (2018). Two-step benchmarking: Setting more realistically achievable targets. Expert Systems with Applications, 92, 124–131.

    Google Scholar 

  • Sànchez, C., & Villarroya, J. M. (2000). Efficiency, technical change and productivity in the european rail sector: A stochastic frontier approach. International Journal of Transport Economics, 27(1), 55–76.

    Google Scholar 

  • Sarac, S. B., Atici, K. B., & Ulucan, A. (2022). Elasticity measurement on multiple levels of DEA frontiers: An application to agriculture. Journal of Production Analysis, 57, 313–324.

    Google Scholar 

  • Schuckmann, S. W., Gnatzy, T., Darkow, I. L., & Von der Gracht, H. A. (2012). Analysis of factors influencing the development of transport infrastructure until the year 2030- A Delphi based scenario study. Technological Forecasting & Social Change, 79(8), 1373–1387.

    Google Scholar 

  • Seiford, L. M., & Zhu, J. (1999). Profitability and marketability of the top 55 US commercial banks. Management Science, 45(9), 1270–1288.

    Google Scholar 

  • Seiford, L. M., & Zhu, J. (2003). Context-dependent data envelopment analysis-measuring attractiveness and progress. Omega, 31(5), 397–408.

    Google Scholar 

  • Sueyoshi, T., Machida, H., Sugiyama, M., Arai, T., & Yamada, Y. (1997). Privatization of Japan national railways: DEA time series approaches. Journal of the Operations Research Society of Japan, 40, 202–205.

    Google Scholar 

  • Sumo, P. D., Ji, X., & Cai, L. (2023). Performance prediction of a textile reverse logistics system using DEA and ANFIS hybrid models. Journal of Intelligent & Fuzzy Systems, (Preprint), 1–11.

  • Takagi, T., & Sugeno, M. (1983). Derivation of fuzzy control rules from human operator’s control actions. IFAC Proceedings Volumes, 16(13), 55–60.

    Google Scholar 

  • Tian, Y., & Li, J. (2023). Improvement pathways for urban land use efficiency in the Beijing-Tianjin-Hebei urban agglomeration at the county level: A context-dependent dea based on the closest target. International Journal of Environmental Research and Public Health, 20(5), 4429.

  • Tomikawa, T., & Goto, M. (2022). Efficiency assessment of Japanese National Railways before and after privatization and divestiture using data envelopment analysis. Transport Policy., 118, 44–55.

    Google Scholar 

  • Vapnik, V. N., Golowich, S., & Smola, A. (1997). Support vector method for function approximation, regression estimation, and signal processing. Advances in Neural Information Processing Systems, 9, 281–287.

    Google Scholar 

  • Wanke, P., & Azad, M. A. K. (2018). Efficiency in Asian railways: A comparison between data envelopment analysis approaches. Transportation Planning and Technology, 41(6), 573–599.

    Google Scholar 

  • Wetzel, H. (2008). European railway deregulation: the influence of regulatory and environmental conditions on efficiency, Working Paper Series in Economics, No. 86, Leuphana Universität Lüneburg, Institut für Volkswirtschaftslehre, Lüneburg.

  • Wu, C., Zhang, N., & Xu, L. (2021). Travelers on the railway: An economic growth model of the effects of railway transportation infrastructure on consumption and sustainable economic growth. Sustainability, 13(12), 6863.

    Google Scholar 

  • Yadegaridehkordi, E., Hourmand, N., & M., Shuib, L., Ahanic, A., Ibrahim, O. (2018). Influence of big data adoption on manufacturing companies’ performance: An integrated DEMATEL-ANFIS approach. Technological Forecasting and Social Change, 137, 199–210.

    Google Scholar 

  • Yu, M. M. (2008). Assessing the technical efficiency, service effectiveness, and technical effectiveness of the world’s railways through NDEA analysis. Transportation Research Part a: Policy and Practice, 42(10), 1283–1294.

    Google Scholar 

  • Zhu, N., Zhu, C., & Emrouznejad, A. (2021). A combined machine learning algorithms and DEA method for measuring and predicting the efficiency of Chinese manufacturing listed companies. Journal of Management Science and Engineering, 6, 435–448.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Business Administration, Recep Tayyip Erdoğan University, Rize, Türkiye

    Süleyman Çakır

Authors
  1. Süleyman Çakır
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Süleyman Çakır.

Ethics declarations

Conflict of interest

The authors have no relevant financial or non-financial interests to disclose.

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors.

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

Çakır, S. Best output prediction in OECD railways using DEA in conjunction with machine learning algorithms. Ann Oper Res 335, 59–77 (2024). https://doi.org/10.1007/s10479-023-05668-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10479-023-05668-w

Keywords

JEL Classification

Search

Navigation