2021· International Journal of Machine Learning and Predictive Analytics· Vol 4, pp. 01-10· 0 citations
TL;DR
Experiments demonstrate the effectiveness of AI-based predictions in improving software quality assessment, providing actionable insights, and supporting proactive maintenance strategies in improving software quality assessment and reducing maintenance effort.
Abstract
Software maintainability is a critical quality attribute that directly impacts the long-term cost, reliability, and evolution of software systems. Predicting maintainability early in the development lifecycle enables developers and managers to make informed design decisions, allocate resources efficiently, and reduce technical debt. This paper investigates the use of artificial intelligence (AI) models for predicting software maintainability based on code metrics, historical project data, and architectural characteristics. We explore supervised learning techniques, including regression models, decision trees, and neural networks, as well as ensemble and hybrid approaches, to estimate maintainability scores and identify key factors influencing maintainability. Experiments on open-source and industrial datasets demonstrate the effectiveness of AI-based predictions in improving software quality assessment, providing actionable insights, and supporting proactive maintenance strategies. The study highlights the potential of AI-driven methods to enhance software engineering practices and reduce maintenance effort.
This research proposes an Explainable Machine Learning (XML)–based framework to assess software quality by integrating code metrics, defect datasets, and advanced interpretability methods such as SHAP, LIME, and permutation importance.
Nandhini Ravi· International Journal of Mac...· 0 citations
Risk assessment is a critical component of the Software Development Lifecycle (SDLC) to ensure timely delivery, maintain quality, and reduce project failures. Traditional risk assessment approaches rely heavily on expert judgment and manual analysis, which can be subjective and prone to errors. This paper proposes a Machine Learning (ML)-based risk assessment framework for SDLC, leveraging historical project data and software metrics to predict potential risks at different stages of development. Several ML algorithms, including Random Forest, Support Vector Machine, and Neural Networks, are evaluated for their effectiveness in identifying high-risk components. Experimental results demonstrate that the proposed approach can enhance risk prediction accuracy, support proactive mitigation strategies, and improve overall software project success rates. The framework provides a scalable and data-driven solution for early risk detection in modern software engineering practices.
Arvind S. Menon, K. Raman· International Journal of Mac...· 0 citations
Software reliability remains a major concern in modern software engineering due to the increasing complexity of software systems and the rapid pace of development. Software Failure Prediction (SFP) aims to identify fault-prone modules before deployment, enabling organizations to reduce maintenance costs and improve system quality. Artificial Intelligence (AI) and Machine Learning (ML) techniques provide data-driven approaches for analyzing software metrics, defect repositories, and execution logs to predict failures. This review examines AI/ML-based approaches for software failure prediction and efficiency optimization, with explicit attention to benchmark datasets, dataset quality, preprocessing, class imbalance, feature selection, model families, validation strategies, and evaluation measures. Representative NASA and PROMISE/Jureczko datasets are characterized in terms of software-unit type, metric families, binary defect labels, and imbalance. The review emphasizes Precision, Recall, F1-score, ROC-AUC, and MCC in addition to accuracy and compares traditional ML, ensemble, and deep-learning approaches. It further discusses missing data, concept drift, and cross-project prediction as key factors affecting real-world generalization. The analysis indicates that no single model is universally optimal; robust software failure prediction requires dataset-aware preprocessing, leakage-safe validation, imbalance-aware evaluation, and an explicit trade-off among predictive performance, computational efficiency, and interpretability.
Prasad Mathapati, S. G. Gollagi, Zebashireen Fahim Shaikh· International journal of res...· 0 citations
An intelligent machine learning-based bug prediction framework that uses SMOTE for dataset balancing and feature selection to identify the most relevant software metrics and uses advanced ensemble learning techniques, such as CatBoost, LightGBM, and the Stacking Ensemble model, to improve prediction accuracy.
Bhukya Yashaswini· International Journal of Eng...· 0 citations
The analysis indicates that combining predictive defect-risk scores with automated test selection can potentially reduce redundant testing, concentrate computational resources on high-risk software components, and improve feedback speed, but model reliability depends on historical defect data, feature quality, distributional stability, explainability, and integration with existing development pipelines.
Haruto Tanaka, Yuki Nakamura· Frontiers in Emerging Multid...· 0 citations
Technical debt represents a persistent challenge in software engineering, characterized by design decisions that increase long-term maintenance costs and reduce software quality. This study evaluates whether AI-assisted refactoring prioritization can reduce technical debt more effectively than traditional rule-based static analysis, using cyclomatic complexity, maintainability index, and remediation effort as debt indicators. Across a dataset of 120,000 code samples and six real Java source files, AI-assisted prioritization achieves 18%–89% greater cumulative complexity reduction compared to rule-based baselines. Beyond software quality, this work contributes to the emerging field of digital knowledge documentation by demonstrating how intelligent, structured analysis tools can preserve and improve access to complex technical information assets over time.
Alexander I. Iliev, Shamshad Mallick, Gagan Ganesh· Digital Presentation and Pre...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
