Story Points Prediction in Agile Software Development Using Machine Learning Models.

Saved in:

Bibliographic Details
Title:	Story Points Prediction in Agile Software Development Using Machine Learning Models.
Authors:	Yehia, Engy¹ engy_yehia@commerce.helwan.edu.eg, Eldanasory, Naglaa A.² Naglaa.Aly21@commerce.helwan.edu.eg, Idrees, Amira M.³ aidrees@kku.edu.sa
Source:	IAENG International Journal of Computer Science. Feb2026, Vol. 53 Issue 2, p539-556. 18p.
Subjects:	Agile software development, Machine learning, Regression analysis, Feature selection, Model validation, Decision trees, Prediction models
Abstract:	Story points serve as the primary metric for evaluating the effort required to implement user stories or resolve issues in agile software development. Despite their significance, research focusing on machine learning (ML)-based approaches for story point estimation remains limited. Although ML techniques have the potential to improve the accuracy and efficiency of story point estimation, their practical implementation and comprehensive evaluation are still underexplored. This study aims to predict user story points using four machine learning models: Decision Tree, Random Forest, Linear Regression, and Neural Network. The research aggregates key characteristics of user stories, assesses feature importance through systematic feature selection methods, and evaluates model performance using multiple metrics, including R-squared (R²), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE). The results demonstrate that Linear Regression achieves superior performance compared to the other models, followed by Neural Networks and Random Forests. In contrast, the Decision Tree model exhibits the lowest predictive accuracy among the evaluated approaches. [ABSTRACT FROM AUTHOR]
	Copyright of IAENG International Journal of Computer Science is the property of International Association of Engineers (IAENG) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	Story points serve as the primary metric for evaluating the effort required to implement user stories or resolve issues in agile software development. Despite their significance, research focusing on machine learning (ML)-based approaches for story point estimation remains limited. Although ML techniques have the potential to improve the accuracy and efficiency of story point estimation, their practical implementation and comprehensive evaluation are still underexplored. This study aims to predict user story points using four machine learning models: Decision Tree, Random Forest, Linear Regression, and Neural Network. The research aggregates key characteristics of user stories, assesses feature importance through systematic feature selection methods, and evaluates model performance using multiple metrics, including R-squared (R²), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE). The results demonstrate that Linear Regression achieves superior performance compared to the other models, followed by Neural Networks and Random Forests. In contrast, the Decision Tree model exhibits the lowest predictive accuracy among the evaluated approaches. [ABSTRACT FROM AUTHOR]
ISSN:	1819656X