EUVIMEDEUVIMED entdecken
Crossref

Enhancing Agile Software Engineering through Predictive Modeling: A Comparative Study of Random Forest and Gradient Boosting Techniques

Rajendra Kattunga

International Journal of Agile Software Engineering · 2026 · 1 (1) · 1-8

DOI: 10.55124/ijas.v1i1.102 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Agile Software Engineering, 2026. Verfasst von Rajendra Kattunga.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Agile software development has completely changed the paradigm of software development in the modern era by incorporating flexibility, iteration, and effective collaboration between various stakeholders of the software development process. Unlike the traditional linear approach, agile methodologies allow the software development process to incorporate flexibility in adapting to changing requirements, making them highly suitable for today’s fast-changing business environment. The current study aims to incorporate machine learning algorithms within the agile environment with the objective of improving the prediction accuracy of key performance indicators, i.e., story points and team velocity. In this regard, the study has utilized Random Forest Regression and Gradient Boosting Regression algorithms for analyzing the data related to sprints, team size, story points committed, defects, and velocity. The data set that has been utilized in the present study contains various sprint cycles, which incorporate the necessary agile metrics that affect the project outcome. From the analysis, it has been found that the variables are highly correlated, as an increase in team size and workload may result in increased productivity, but it may also cause an increase in defects. The Random Forest model has shown high predictive accuracy, as it has the ability to generalize well, while the Gradient Boosting model has achieved almost perfect accuracy during the training phase but has shown some over fitting during the testing phase. The findings of the study show that the integration of agile methodologies with advanced predictive models has the ability to improve decision-making, optimize resources, and also improve the quality of the software product. Keywords: Agile Software Engineering, Machine Learning, Random Forest Regression, Gradient Boosting, Story Point Prediction, Software Project Management.

Zitieren

APA

Kattunga, R. (2026). Enhancing Agile Software Engineering through Predictive Modeling: A Comparative Study of Random Forest and Gradient Boosting Techniques. International Journal of Agile Software Engineering, 1(1), 1-8. https://doi.org/10.55124/ijas.v1i1.102

Vancouver

Kattunga R. Enhancing Agile Software Engineering through Predictive Modeling: A Comparative Study of Random Forest and Gradient Boosting Techniques. International Journal of Agile Software Engineering. 2026;1(1):1-8. doi:10.55124/ijas.v1i1.102

BibTeX
@article{Kattunga2026,
  author = {Kattunga, Rajendra},
  title = {Enhancing Agile Software Engineering through Predictive Modeling: A Comparative Study of Random Forest and Gradient Boosting Techniques},
  journal = {International Journal of Agile Software Engineering},
  year = {2026},
  volume = {1},
  number = {1},
  pages = {1--8},
  doi = {10.55124/ijas.v1i1.102}
}
Kostenlos starten →