Comparison of Predicted and Actual Data Values Using HGBR and XGBR Models
Journal of Software Quality Engineering and DevOps · 2026 · 1 (1) · 1-8
DOI: 10.55124/jsqd.v1i1.103 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Software Quality Engineering and DevOps, 2026. Verfasst von Kiran Kumar Mandula Samuel.
Abstract (Originalsprache)
The prediction of software Quality Score is carried out using advanced machine learning models, considering specific software development and execution parameters. The input parameters selected are Code Complexity, Test Coverage (%), and Deployment Frequency, which are major factors in software development. Two advanced regression models, Histogram Gradient Boosting Regressor (HGBR) and Extreme Gradient Boosting Regressor (XGBR), are used to analyze the output parameter, Quality Score. Research Significance: Software quality is a key success criterion for software applications in the modern era, and it has a direct impact on the reliability, maintainability, and satisfaction of software applications. This research has provided a data-driven understanding of the impact of software development metrics on software quality, and it has provided insights into the optimization of software engineering techniques by applying machine learning algorithms. Methodology: The study employs a systematic approach based on the concept of machine learning. First, the study uses a dataset containing software parameters like Code Complexity, Test Coverage (%), Deployment Frequency, and Quality Score. It performs Exploratory Data Analysis (EDA) to understand the relationships between the parameters. It splits the dataset into the training and testing sets. Alternative (Input and Output Parameters): Input Parameters:Code Complexity, Test Coverage (%), Deployment Frequency, Output Parameter (Evaluation):Quality Score Results: From the results provided in the figure above, it is clear that both models perform exceptionally in predicting the quality of the software. The HGBR model performs with a high degree of accuracy and a high degree of generalization, as seen in the test performance of the model. The XGBR model performs almost perfectly on the training set but shows a slightly lower degree of accuracy on the test set. This could imply that the model is overfitting the training data. Conclusion: This study has shown that it is possible for machine learning algorithms to be effectively used in predicting software quality, as measured by critical software development factors. Of the algorithms tested, HGBR appears to be a better choice in terms of a trade-off between accuracy and generality.
Zitieren
APA
Samuel, K. K. M. (2026). Comparison of Predicted and Actual Data Values Using HGBR and XGBR Models. Journal of Software Quality Engineering and DevOps, 1(1), 1-8. https://doi.org/10.55124/jsqd.v1i1.103
Vancouver
Samuel KKM. Comparison of Predicted and Actual Data Values Using HGBR and XGBR Models. Journal of Software Quality Engineering and DevOps. 2026;1(1):1-8. doi:10.55124/jsqd.v1i1.103
BibTeX
@article{Samuel2026,
author = {Samuel, Kiran Kumar Mandula},
title = {Comparison of Predicted and Actual Data Values Using HGBR and XGBR Models},
journal = {Journal of Software Quality Engineering and DevOps},
year = {2026},
volume = {1},
number = {1},
pages = {1--8},
doi = {10.55124/jsqd.v1i1.103}
}
EUVIMED