Project management methodologies are widely used to structure development processes and increase the likelihood of project success. However, the incorrect selection of methodology remains an underestimated factor contributing to project failure. This study explores the correlation between project outcomes and methodology choice through a filled in targeted questionnaire distributed to project management professionals. The results reveal weak but notable correlations and suggest that adapting methodology during a project can significantly increase success rates. Based on the collected data, a mathematical design for an intelligent information sub-system is proposed with usage of Laplace smoothing and synthetic example, aimed at supporting project managers in selecting the most suitable methodology for future projects. The sub-system relies on empirical data and simple predictive calculations to provide evidence-based recommendations tailored to specific project parameters.
In the contemporary landscape of information technology, virtually all development activities are conducted within the framework of structured project management methodologies. These methodologies serve a critical role in bringing order, predictability, and strategic planning to complex development processes, thereby increasing the likelihood of achieving project objectives within predefined constraints such as time, budget, and quality. The use of project management principles is not confined solely to the IT sector; it has also been widely adopted across various industries and domains, including construction, healthcare, education, and public administration. In all these fields, project management is employed with the common goal of enhancing the efficiency, transparency, and success rate of projects.
As projects continue to grow in scale, complexity, and interdependency, the corresponding evolution of project management practices has become both necessary and inevitable. Traditional methodologies such as Waterfall and PRINCE2, while still relevant in specific contexts, are increasingly being complemented or replaced by more flexible, iterative frameworks. In particular, the emergence of methodologies under the Agile umbrella, such as Scrum, Kanban and Hybrid, has significantly transformed the way organizations approach project planning and execution. These methodologies emphasize adaptability, continuous feedback, and close collaboration between stakeholders, and have been widely embraced by both small enterprises and multinational corporations.
Simultaneously, a broad range of software tools and platforms have been developed to support the planning, monitoring, and control of project activities. Despite these advancements in both theory and practice, project failure remains a persistent issue across industries. Projects may fail due to various reasons, including unclear objectives, inadequate resource allocation, stakeholder misalignment, or insufficient risk management. One particularly critical, yet often underestimated, factor contributing to project failure is the inappropriate selection or application of a project management methodology. Choosing a methodology that does not align with the specific characteristics of a given project can significantly undermine its chances of success.
At present, there is a notable absence of intelligent, adaptive information systems designed to assist project managers in selecting the most suitable project management methodology for their specific context. Such a system could potentially analyze past project data, identify patterns and correlations, and provide evidence-based recommendations tailored to the unique parameters of a new project. The aim of this work is to present the conceptual foundation and key components of such a system, exploring how it can contribute to more informed decision-making and, ultimately, to improved project outcomes.
The phenomenon of project failure has been the subject of extensive academic investigation across
multiple disciplines, particularly within the fields of management science and information
technology. Prior studies, such as those conducted by various scientist [
One particularly under explored area in this context is the correlation between the application
of an inappropriate project management methodology and project failure. Although the issue has
been acknowledged in passing within the scientific research [17], there has been a lack of
systematic, empirical research explicitly designed to isolate and quantify this relationship [
While a number of existing surveys have attempted to explore project-related challenges [
project industry
Scrum – 60%; Kanban – 4,71%; Waterfall – 4,71%; Hybrid – 18,82%; No methodology – 4,71%; Other – 7,06% 29,41%
0,069 Weak correlation
-0,02 No correlation Tech -12,5%; Healthcare – 57,14%; Retail – 0%; Finance – 30%; Transportation – 0%; Food and beverages – N/A; Logistics – 25%; E-Commerce – 33,33%; Edtech – 100%; Government – N/A%; Oil&Gas – 66,67%; Manufacturing – 0%; Other – 60%
Despite the overall weak correlation between project failure and incorrect methodology choice, an auxiliary calculation revealed a substantial insight: projects that underwent a successful change in methodology experienced a 30.1% increase in the probability of success. This finding, while preliminary, underscores the potential value of dynamic methodology reassessment throughout the project life cycle.
In addition to offering insight into present trends, the collected data will also serve as a
foundational reference for the continuation of development of an intelligent information system
designed to assist project managers in selecting the most appropriate methodology for their
projects [
Sub-system that is responsible for calculating suggestion for project success based on short list of questions that will be asked through the interface of information system. Those questions are listed in Table 2 below. And suggestions are based on most common project management methodologies such as Scrum, Kanban, Waterfall and Hybrid [13,14].
After receiving the data from mentioned shortlisted questionnaire sub-system will start to perform calculations according to this formula:
5 P¿=max ∑ M i ∙ Pd ∙ Ps ∙ Pn ∙ Pind
i=1 where P¿ is probability based on inputs [15], M i is success-based rate of methodology, Pd is project duration likelihood based on input value, Ps is project size likelihood based on input value, Pn is project nature likelihood based on input value, Pind is project industry likelihood based on input value.
Success based rate of methodology can be calculated with help of next formula: (1) (2) (3) (4) (5) M i=
CR= Pc h ange
Pd j= 5
where Psuccess is quantity of success projects with i-methodology, Pall is all projects with imethodology and CR is change rate, value of projects that changed method from i-methodology. It calculates with this formula: where Pc h ange is quantity of projects with i-methodology changed.
Likelihood based variables different set of formulas will be used. But since in the data there some gaps in some answers, like absence of some of industries Laplace smoothing will be used to avoid zero probabilities in calculations. For likelihood of project duration formula will be next: where Pd jis j value for project duration according to values in data (in other words likelihood for 1 year project duration, less than year, 2+ years), Psuccessj is quantity of successful projects with given j value and α is Laplace smoothing, in current case it’s equals 1. J in case of duration equals 3.
where Psjis j value for project size according to values in data (small, medium, large). In this case j equals 3.
Pnj= 5
Results shown in this table are static and provide logic of overall calculations, because this step of stating quantity of the project successes should be repeated for other parameters such as Nature, Duration and Industry.
Same calculations should be repeated to calculate Pd j, Pnj and Pind j. They will not be presented in this article due to it repetitive nature and partial confidentiality of the data. After calculations P¿ can be calculated. For instance if input values are (Less than Year; Small; KTLO/Support; Oil&Gas) max value of P¿ will be for Scrum with 0.002324 value.
This study demonstrates the potential of using systematically gathered empirical data to inform the selection of project management methodologies for future projects. By analyzing correlations between specific project characteristics, risk factors, and outcomes from past initiatives, it becomes possible to calculate the likelihood of success associated with particular methodologies in new project contexts. The proposed approach lays the groundwork for a methodology-assistive information system capable of supporting project managers in making evidence-based decisions at the planning stage.
Such a system would be particularly valuable in environments where project conditions are ambiguous or where the project manager lacks historical organizational data to guide their choices. By providing data-driven recommendations, the system can act as a decision-support tool that complements professional judgment rather than replacing it.
Also, the ability to quantitatively estimate the suitability of different methodologies based on minimal input about an upcoming project introduces a layer of predictive analytics into the traditionally experience-driven field of project management. As a result, organizations may benefit from enhanced planning efficiency, more strategic risk mitigation, and improved alignment between project approach and project complexity, size, or industry.
Future work may focus on refining the predictive model by applying machine learning techniques to continuously improve the accuracy of recommendations. The developed sub-system of information system could also be integrated with project management platforms, making it a seamless component of project initiation workflows
Ihor Berezutskyi would like to express his deepest gratitude to his wife, Hanna Zaviriukha, whose relentless work helped him to keep organized and focused on the main research. She also challenged few aspects of this work and helped to identify some weakness in logic and helped to resolve them.
Ihor Berezutskyi also want to thank his daughter Elizaveta Zaviriukha for her talent to lighted mood in any of the cases and for bringing tea and coffee when needed.
Ihor Berezutskyi want to thank all project managers who helped him with filling questionnaire and provided valid critic on some of the questions formulation.
During the preparation of this work, the authors used ChatGPT in order to: Paraphrase and reword. After using this tool/service, the authors reviewed and edited the content as needed and takes full responsibility for the publication’s content. [7] Mihaylenko, V., Borodavka, Y., Dolya, E., Savenko, V. Information tools for project management of the building territory at the stage of urban planning, CEUR Workshop Proceedings, 2021, 2851, рр. 22–33, http://ceur-ws.org/Vol-2851/paper3.pdf [8] S. Bushuyev, K. Pilyugina,I. Achkasov, A. Zaprivoda, Clip Thinking in the Digital Age: Complimentary or Contradictory, 2023 IEEE 18th International Conference on Computer Science and Information Technologies (CSIT), 2023. DOI: 10.1016/j.procs.2023.12.210 [9] Khan, A., Hasana, M.K., Ghazal, T.M., Islam, S., Alzoubi, H.M., Mokhtar, U.A., Alam, R., Ahmad, M., 2022. Collaborative Learning Assessment via Information and Communication Technology, in: Proceedings, RIVF 2022., pp. 311-316 [10] S. Bushuyev, N. Bushuyeva, D. Bushuiev, V. Bushuieva, Integrated Intelligence Model for Assessment Digital Transformation Project, 2023 IEEE International Conference on Smart Information Systems and Technologies (SIST), 2023. DOI:10.1109/SIST58284.2023.10223578 [11] M. El Khatib, A. Al Falasi, Effects of Artificial Intelligence on Decision Making in Project
Management, American Journal of Industrial and Business Management 11, 2021, pp. 251-260. [12] Harvard Business Review Analytic Services, The Evolution of Decision Making: How Leading Organizations Are Adopting a Data-Driven Culture. URL: https://hbr.org/resources/pdfs/tools/17568_HBR_SAS%20Report_webview.pdf [13] R. Nicoara, Project Management Methods, 2023, DOI: 10.1007/978-1-4842-9663-9_12 [14] R. L. Moura, T. C. J. Carneiro, T. L. Dias, VUCA environment on project success: The effect of project management methods, Brazilian Business Review 20(3), 2023, DOI: 10.15728/bbr.2023.20.3.1.en [15] M. Nekrasova, Using methods of probability theory and mathematical statistics in project management, Bulletin of the National Technical University «KhPI» Series Dynamics and Strength of Machines, 2023, DOI: 10.20998/2078-9130.2023.2.293040 [16] S. Turney Pearson Correlation Coefficient (r). Guide & Examples, 2024 https://www.scribbr.com/statistics/pearson-correlation-coefficient/ [17] I. Berezutskyi, Method for analyzing project characteristics, Management of Development of
Complex Systems, Kyiv, 2025. DOI: 10.32347/2412-9933.2025.61.145-150 [18] Aliyev, Ali. The AI and Quantum Era: Transforming Project Management Practices. Journal of
Future Artificial Intelligence and Technologies 1.4 (2025): 348-370 [19] Y. Riabchun, T. Honcharenko, V. Honta, K. Chupryna, O. Fedusenko. Methods and means of evaluation and development for prospective students’ spatial awareness, International Journal of Innovative Technology and Exploring Engineering, 8(11), 2019, pp. 4050–4058 DOI: 10.35940/ijitee.K1532.0981119 [20] М. Gladka, О. Kuchanskyi, М. Kostikov, R. Lisnevskyi, "Method of Allocation of Labor Resources for IT Project Based on Expert Assessements of Delphi", SIST 2023 - 2023 IEEE International Conference on Smart Information Systems and Technologies, Proceedings, pp. 545 - 551, 2023. DOI: 10.1109/sist58284.2023.10223549