Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM65902
Volume:
10 |
7 |
Jul 2026
Pages:
1-9
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
MBA
RAJALAKSHMI ENGINEERING COLLEGE
MBA
RAJALAKSHMI ENGINEERING COLLEGE
Background: Traditional project planning methodologies often rely on subjective, experience-based estimations that struggle to account for the non-linear interdependencies of complex project environments. This "granularity gap" leads to reactive management and systemic schedule delays. Objective: This study applies AI-driven predictive analytics to identify delay-prone activities at a granular, task-level scale, transitioning project governance from intuition to data-driven oversight. Methodology: A dataset of 150 task-level observations across functional departments (Welding, Procurement, Integration, etc.) was analyzed using a Random Forest Regression model. The research evaluated four key predictors: task duration, complexity, risk level, and dependency. Results: The model demonstrated high predictive accuracy, achieving a Coefficient of Determination (R²) of 0.90. Statistical analysis revealed that inter-task dependency (r = 0.61) is the primary driver of delay, whereas task duration showed a negligible correlation (r = 0.05). Conclusion: The findings suggest that project connectivity is a more reliable predictor of schedule integrity than individual task duration. Implementing dependency-aware AI models allows managers to proactively mitigate "cascading delays" before execution begins.
KEYWORDS
This study has successfully demonstrated that AI-driven predictive analytics can transcend the limitations of traditional, experience-based project planning. By utilizing a Random Forest Regression model, the research achieved an R² of 0.90, statistically validating the shift from deterministic scheduling to probabilistic forecasting. The most significant finding is the identification of inter-task dependency (r = 0.61) as the primary driver of schedule variance, effectively debunking the traditional reliance on duration (r = 0.05) as the sole planning metric.
1. Kahneman D., Tversky A., "Prospect Theory: An Analysis of Decision under Risk", Econometrica, 1979, 47 (2), 263-291. 2. Flyvbjerg B., "Top Ten Behavioral Biases in Project Management", Project Management Journal, 2021, 52 (6), 531-546. 3. Williams T., "The Complexity of Projects and Delays", International Journal of Project Management, 2017, 35 (4), 500-512. 4. Pinto J.K., Winch G.M., "The Planning Fallacy in Large Infrastructure Projects", Strategic Management Journal, 2016, 37 (8), 1530-1545. 5. Atkinson R., "Project Management: Cost, Time and Quality, Two Best Guesses and a Phenomenon, Its Time to Accept Other Criteria", International Journal of Project Management, 1999, 17 (6), 337-342. 6. Wauters M., Vanhoucke M., "A Comparative Study of Machine Learning Methods for Project Duration Forecasting", Automation in Construction, 2016, 71, 120-136. 7. Khosrowshahi F., "Neural Networks in Project Duration Estimation", Journal of Construction Engineering, 2017, 43 (2), 89-101. 8. Voznytsia M., "AI Risk Patterns in Modern Planning Frameworks", Journal of Decision Systems, 2024, 33 (1), 45-62. 9. Gondia A., Siaahlooei A., Varajao J., "Predicting Project Delays Using Machine Learning Ensemble Methods", Methodologies in Systems Engineering, 2020, 22 (3), 114-128. 10. Li H., Zhang X., Liu Y., "Random Forest Frameworks for Structural High-Dimensional Complex Environment Mapping", Advanced Engineering Informatics, 2021, 49, 101-115.
Publication Date
7/8/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
1
Total views since publication
PDF Downloads
12
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...