Machine learning technologies have recently emerged as transformative tools for enhancing project management accuracy and efficiency. This study introduces a data-driven model that leverages the hybrid eXtreme Gradient Boosting-Simulated Annealing (XGBoost-SA) algorithm to predict the time and cost of construction projects. By accounting for the complexity of activity networks and uncertainties within project environments, the model aims to address key challenges in project forecasting. Unlike traditional methods such as Earned Value Management (EVM) and Earned Schedule Method (ESM), which rely on static metrics, the XGBoost-SA model adapts dynamically to project data, achieving 92% prediction accuracy. This advanced model offers a more precise forecasting approach by incorporating and optimizing features from historical data. Results reveal that XGBoost-SA reduces cost prediction error by nearly 50% and time prediction error by approximately 80% compared to EVM and ESM, underscoring its effectiveness in complex scenarios. Furthermore, the model’s ability to manage limited and evolving data offers a practical solution for real-time adjustments in project planning. With these capabilities, XGBoost-SA provides project managers with a powerful tool for informed decision-making, efficient resource allocation, and proactive risk management, making it highly applicable to complex construction projects where precision and adaptability are essential. The main limitation of the developed model in this study is the reliance on data from similar projects, which necessitates additional data for application to other industries.

One of the fundamental challenges in managing software and information technology projects is monitoring and predicting project status at the end of each sprint, release or project. Agile project management has emerged over the past two decades, significantly impacting project success. However, no comprehensive approach based on the features of this approach has been found in studies to monitor and predict the status of a sprint, release or project. This study aims to develop a data-driven approach for predicting the status of software projects based on agility features. For this purpose, 22 agility features were first identified to evaluate and predict the status of projects in four aspects: Endurance, Effectiveness, Efficiency, and Complexity. The findings indicate that the aspects of Effectiveness and Efficiency have the greatest impact on project success. Additionally, the results show that features related to team work, team capacity, experience and project objectives have the most significant impact on project success. An artificial neural network algorithm was then used, and a model was developed to predict project status, which was optimized using the Neural Architecture Search algorithm with a 93 percent accuracy rate. The neural network model was interpreted using the SHapley Additive exPlanations (SHAP) algorithm, and sensitivity analysis was performed on the important components. Finally, the behavior of the projects in each category was analyzed and evaluated using the Apriori algorithm.

Agile outcome models commonly map Jira variables directly to a retrospective label and then explain the prediction through fragmented feature attributions; they rarely separate domain concepts, team clustering, unresolved work, and concept-label coupling. This study evaluates a domain-informed, concept-bottleneck-style explainable AI architecture for retrospective diagnosis of Agile Epic outcomes. A frozen Jira export of 10,000 unique issue-level records was linked to a pre-specified analytical cohort of 180 Epics across 14 teams. Six experts rated efficiency, effectiveness, sustainability, and contextual risk, while outcomes were recorded as Successful, Challenged, or Unsuccessful. Because the outcome labels and concept ratings were informed by the same Jira evidence, the models estimate consistency with an expert labelling procedure, rather than independent project success. Under five-fold group-aware cross-validation, the fixed-configuration flat LightGBM achieved macro-F1 = 0.864 ± 0.053 and the fixed-configuration HMXAI/CBM-style model achieved 0.843 ± 0.084. These descriptive primary scores are not a joint nested-model-selection comparison. The proposed method, therefore does, not demonstrate a performance improvement; its contribution is an inspectable diagnostic structure. Performance fell materially on the resolved-only subset (LightGBM macro-F1 = 0.645), and model-specific nested, leave-one-team-out, calibration, uncertainty, correlation, and intervention analyses further bound the claims. Concept interventions were not uniformly monotone, so the concept layer is domain-interpretable in form but not yet user-validated as actionable. The study contributes a transparent audit of when concept-level diagnosis can complement flat classification and when circularity, censoring, and shortcut learning restrict interpretation.