BUSINESS INFORM JOURNAL.

УКР

ENG

Search:

REGISTRATION CERTIFICATE

KV #19905-9705 PR dated 02.04.2013.

FOUNDERS

RESEARCH CENTER FOR INDUSTRIAL DEVELOPMENT PROBLEMS of NAS of Ukraine (KHARKIV, UKRAINE)

ROR

EDRPOU 05481984

According to the decision No. 802 of the National Council of Television and Radio Broadcasting of Ukraine dated 14.03.2024, is registered as a subject in the field of print media.
ID R30-03156

PUBLISHER

Liburkina L. M.

CATALOG

Machine Learning for Early Warning of Budget Overruns in Investment Projects
Proniakin Y. V., Pronoza P. V.

Proniakin, Yehor V., and Pronoza, Pаvlo V. (2026) “Machine Learning for Early Warning of Budget Overruns in Investment Projects.” Business Inform 9:197–210.
https://doi.org/10.32983/2222-4459-2026-9-197-210

Section: Investment Processes

Article is written in Ukrainian
Downloads/views: 0

Download article (pdf) -

UDC 005.8:330.322.01:004.85

Abstract:
The article substantiates a methodological approach to forecasting investment project budget deviations using machine learning and develops a mechanism for embedding it into the project financial control function. The relevance stems from the systemic nature of cost escalation, whose persistence has not diminished despite decades of refinement in cost estimation practice, and from the reactive design of existing financial control instruments, which generate a signal only after the deviation has materialised in cash flows. The body of research applying machine learning to project cost forecasting is systematised, revealing its concentration on the regression formulation, which does not correspond to the operational requirements of financial controlling. A reformulation into a classification task is proposed: the model estimates the conditional probability that cumulative cost deviation will exceed a materiality threshold within a defined warning horizon, with the threshold anchored to the contingency reserve ratio, which endows it with direct economic meaning. An analytical expression for the optimal decision threshold is derived from the ratio of misclassification costs. It is demonstrated that the conventional threshold of 0.5 is economically justified only under the assumption of equal costs of false positive and false negative errors, an assumption that never holds in an investment context, and that the threshold is project-specific, depending on the financing structure, cost of capital and reserve size. It is further shown that synthetic minority oversampling without subsequent probability recalibration invalidates the economic interpretation of the threshold. A validation procedure is substantiated that eliminates two forms of information leakage inherent in project accounting panel data – group dependence among observations of the same project and model access to future macro-financial regimes – and provides for stage-stratified performance assessment. The predictor space is specified with a distinct macro-financial block, critical under conditions of high inflation and exchange rate volatility.

Keywords: financial management; investment project; investment project management; machine learning.

Tabl.: 5. Formulae: 8. Bibl.: 30.

Proniakin Yehor V. – Applicant, Department of Accounting and Finance, National Technical University «Kharkiv Polytechnic Institute» (2 Kyrpychova Str., Kharkіv, 61002, Ukraine)
Email: [email protected]
Pronoza Pаvlo V. – Doctor of Sciences (Economics), Professor, Professor, Department of Finance and Credit, Simon Kuznets Kharkiv National University of Economics (9a Nauky Ave., Kharkiv, 61165, Ukraine)
Email: [email protected]

List of references in article

Ahiaga-Dagbui D. D. & Smith S. D. (2014). Dealing with construction cost overruns using data mining. Construction Management and Economics, 32(7–8), 682–694. https://doi.org/10.1080/01446193.2014.933854
Al mnaseer R., Al-Smadi S. & Al-Bdour H. (2023). Machine learning-aided time and cost overrun prediction in construction projects: Application of artificial neural network. Asian Journal of Civil Engineering, 24, 2583–2593. https://doi.org/10.1007/s42107-023-00665-7
Alazawy S. F. M., Ahmed M. A. & Raheem S. H. (2025). Explainable machine learning to predict the construction cost of power plant based on random forest and Shapley method. CivilEng, 6(2). https://doi.org/10.3390/civileng6020021
Asiedu R. O., Frempong N. K. & Alfen H. W. (2017). Predicting likelihood of cost overrun in educational projects. Engineering, Construction and Architectural Management, 24(1), 21–39. https://doi.org/10.1108/ECAM-06-2015-0103
Attalla M. & Hegazy T. (2003). Predicting cost deviation in reconstruction projects: Artificial neural networks versus regression. Journal of Construction Engineering and Management, 129(4), 405–411. https://doi.org/10.1061/(ASCE)0733-9364(2003)129:4(405)
Batselier J. & Vanhoucke M. (2016). Practical application and empirical evaluation of reference class forecasting for project management. Project Management Journal, 47(5), 36–51. https://doi.org/10.1177/875697281604700504
Batselier J. & Vanhoucke M. (2017). Improving project forecast accuracy by integrating earned value management with exponential smoothing and reference class forecasting. International Journal of Project Management, 35(1), 28–43. https://doi.org/10.1016/j.ijproman.2016.10.003
Breiman L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
Chawla N. V., Bowyer K. W., Hall L. O. & Kegelmeyer W. P. (2002). SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16, 321–357. https://doi.org/10.1613/jair.953
Chen T. & Guestrin C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). New York: ACM. https://doi.org/10.1145/2939672.2939785
Chen H. L., Chen W. T. & Lin Y. L. (2016). Earned value project management: Improving the predictive power of planned value. International Journal of Project Management, 34(1), 22–29. https://doi.org/10.1016/j.ijproman.2015.09.008
Cheng M.-Y., Peng H.-S., Wu Y.-W. & Chen T.-L. (2010). Estimate at completion for construction projects using evolutionary support vector machine inference model. Automation in Construction, 19(5), 619–629. https://doi.org/10.1016/j.autcon.2010.02.008
Coffie G. H. & Cudjoe S. K. F. (2024). Using extreme gradient boosting (XGBoost) machine learning to predict construction cost overruns. International Journal of Construction Management, 24(16), 1742–1750. https://doi.org/10.1080/15623599.2023.2289754
Colin J. & Vanhoucke M. (2014). Setting tolerance limits for statistical project control using earned value management. Omega, 49, 107–122. https://doi.org/10.1016/j.omega.2014.06.001
Flyvbjerg B., Holm M. K. S. & Buhl S. L. (2002). Underestimating costs in public works projects: Error or lie?. Journal of the American Planning Association, 68(3), 279–295. https://doi.org/10.1080/01944360208976273
Flyvbjerg B., Holm M. K. S. & Buhl S. L. (2004). What causes cost overrun in transport infrastructure projects?. Transport Reviews, 24(1), 3–18. https://doi.org/10.1080/0144164032000080494a
Flyvbjerg B. (2006). From Nobel Prize to project management: Getting risks right. Project Management Journal, 37(3), 5–15. https://doi.org/10.1177/875697280603700302
Flyvbjerg B. (2013). Quality control and due diligence in project management: Getting decisions right by taking the outside view. International Journal of Project Management, 31(5), 760–774. https://doi.org/10.1016/j.ijproman.2012.10.007
Flyvbjerg B. (2014). What you should know about megaprojects and why: An overview. Project Management Journal, 45(2), 6–19. https://doi.org/10.1002/pmj.21409
Hamdan M. M., Thneibat M. & Hyari K. (2026). Predicting cost overrun in construction projects using machine learning algorithms: The case of Jordan. Engineering, Construction and Architectural Management, 33(6), 4732–4763. https://doi.org/10.1108/ECAM-09-2024-1209
Kim G.-H., An S.-H. & Kang K.-I. (2004). Comparison of construction cost estimating models based on regression analysis, neural networks, and case-based reasoning. Building and Environment, 39(10), 1235–1242. https://doi.org/10.1016/j.buildenv.2004.02.013
Love P. E. D., Ahiaga-Dagbui D. D. & Irani Z. (2016). Cost overruns in transportation infrastructure projects: Sowing the seeds for a probabilistic theory of causation. Transportation Research Part A: Policy and Practice, 92, 184–194. https://doi.org/10.1016/j.tra.2016.08.007
Lundberg S. M. & Lee S.-I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems. https://proceedings.neurips.cc/paper_files/paper/2017/file/8a20a8621978632d76c43dfd28b67767-Paper.pdf
Narbaev T., Haz?r O., Khamitova B. & Talgat S. (2024). A machine learning study to improve the reliability of project cost estimates. International Journal of Production Research, 62(12), 4372–4388. https://doi.org/10.1080/00207543.2023.2262051
Nenni M. E., De Felice F., De Luca C. & Forcina A. (2025). How artificial intelligence will transform project management in the age of digitisation: A systematic literature review. Management Review Quarterly, 75, 1669–1716. https://doi.org/10.1007/s11301-024-00418-z
Ostapiuk N. A. & Nikiforenko V. V. (2025). Vykorystannia suchasnykh analitychnykh instrumentiv ta Big Data v otsintsi vartosti pidpryiemstv [Use of modern analytical tools and Big Data in enterprise valuation]. Ekonomika ta suspilstvo, 75. https://doi.org/10.32782/2524-0072/2025-75-42
Panas Ya. V. (2024). Informatsiine zabezpechennia upravlinnia innovatsiinymy proektamy v umovakh tsyfrovoi ekonomiky [Information support for managing innovative projects in the conditions of the digital economy]. Ekonomika ta suspilstvo, 62. https://doi.org/10.32782/2524-0072/2024-62-119
Plebankiewicz E. (2018). Model of predicting cost overrun in construction projects. Sustainability, 10(12). https://doi.org/10.3390/su10124387
Plebankiewicz E. & Wieczorek D. (2020). Prediction of cost overrun risk in construction projects. Sustainability, 12(22). https://doi.org/10.3390/su12229341
Turkyilmaz A. H. & Polat G. (2024). Risk-based completion cost overrun ratio estimation in construction projects using machine learning classification algorithms: A case study. Buildings, 14(11). https://doi.org/10.3390/buildings14113541