[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122455-en":3,"doc-seo-122455-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},122455,1374391974564,"Clementine","https://ap-avatar.wpscdn.com/avatar/14000253aa45c000a9e?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779874745381141002",8,"Research & Report","HYBRID TECHNIQUE FOR SOFTWARE DEFECT PREDICTION USING MACHINE LEARNING TECHNIQUES","Human errors during software development produce many defects, making early detection and reduction essential. Yet existing approaches often underperform in accuracy and generalizability because of class imbalance, limited feature extraction, and computational inefficiency. This study presents a hybrid CNN+LSTM feature extraction method combined with ADASYN for imbalance handling and XGBoost for defect prediction. Experiments on CM1, MC1, KC1, PC1, and PC4 compare against SOTA models, improving recall, F1-score, and AUC-ROC.","HYBRID TECHNIQUE FOR SOFTWARE DEFECT PREDICTION USING MACHINE LEARNING  \nTECHNIQUES  \nDarius T Chinyio 1, *, Martin E Irhebhude 1, Muhammad Jumare Haruna2  \n1 Department of Computer Science, Nigerian Defence Academy, Kaduna, Nigeria.  \n2 Department of Computer Science, Federal University of Education, Zaria, Nigeria.  \n*Corresponding author email: [dtchinyio@nda.edu.ng](dtchinyio@nda.edu.ng)  \nReceived: 29 Mar 2025 Accepted:15 Jun 2025 Published:1Oct 2025 [https://doi.org/10.25271/sjuoz.2025.13.4.1532](https://doi.org/10.25271/sjuoz.2025.13.4.1532)  \nABSTRACT:  \nHuman errors during software development lead to many defects, which emphasizes the importance of early detection and minimization. However, existing approaches often fall short in delivering accurate, scalable, and generalizable predictions due to challenges such as class imbalance, feature extraction limitations, and computational inefficiencies. This study proposes a hybrid method using a Convolutional Neural Network (CNNs) + Long Short-Term Memory (LSTM) for feature extraction, addressing class imbalance with Adaptive Synthetic Sampling (ADASYN) and subsequent training using Extreme Gradient Boosting (XGboost), to predict software defects. The proposed approach was evaluated on five publicly available datasets (CM1, MC1, KC1, PC1, and PC4) and compared with state-of-the-art (SOTA) models. Experimental results demonstrated that the hybrid model significantly outperforms traditional XGBoost-based models in terms of recall, F1-score, and area under the receiver operating characteristic curve (AUC), addressing the shortcomings of existing methods. Results demonstrate the effectiveness of the proposed method, with notable performance metrics achieved across all datasets. For example, on the MC1 dataset, the model attained an accuracy of 0.9980, a precision of 0.9971, a recall of 0.9988, an F1-score of 0.9980, and an AUC-ROC of 0.9999. On the KC1 dataset, it achieved an accuracy of 0.9344, a precision of 0.9265, a recall of 0.9375, an F1-score of 0.9320, and an AUC-ROC of 0.9839. The model achieves better performance than traditional machine learning methods and separate deep learning models, especially in the areas of recall and AUC-ROC. This research presents a robust solution through hybrid approaches that address class imbalance and maintain high predictive accuracy for software development process tasks, offering insights into the trade-offs between machine learning and deep learning methods.  \nKEYWORDS: Software Defect Prediction (SDP), CNN, LSTM, Machine learning, Deep Learning, Hybrid Technique, XGboost  \n1. INTRODUCTION  \nSoftware defects represent faults in computer programs that may lead to system failures, data loss, security vulnerabilities, and financial losses (Elentukh, 2023; Shafiq et al., 2023) . While the terms 'defect', 'bug', and 'error' are sometimes used interchangeably, a defect generally refers to an imperfection in code functionality that may or may not result in a bug, which isan observable deviation from expected behavior during execution. An error, on the other hand, typically refers to a human mistake made during development that leads to defects in the code.  \nDefects not only affect runtime performance and reliability but also compromise key software design principles such as  \nmodularity and separation of concerns. Faulty modules are less likely to be reused due to their instability or unclear functionality, which reduces maintainability and increases technical debt. In this study, the static code features extracted from the datasets (e.g., cyclomatic complexity, coupling, cohesion) reflect structural weaknesses that are closely tied to defect proneness and negatively influence reusability and modular design.  \nAccording to research by Krasner (2021), Mahmoud et al.(2024), and Mehmood et al. (2023), software defects account for half of project expenses, while also causing system breakdownsand security risks, with additional negative impac","cbCaib3M56cbFvDS","https://ap.wps.com/l/cbCaib3M56cbFvDS","pdf",1002289,1,15,"English","en",105,"# Introduction\n## Software defects and their impact\n## Motivation for hybrid machine learning approaches\n## Challenges in existing software defect prediction\n# Method Overview\n## Feature extraction with CNN and LSTM\n## Class imbalance handling with ADASYN\n## Prediction with XGBoost\n# Experimental Evaluation\n## Datasets used (CM1, MC1, KC1, PC1, PC4)\n## Comparison with SOTA models\n## Performance metrics (recall, F1-score, AUC-ROC)","[{\"question\":\"Why is early software defect prediction important?\",\"answer\":\"Software defects can trigger system failures, data loss, security vulnerabilities, and financial losses. Early detection reduces runtime reliability problems and technical debt risks.\"},{\"question\":\"What hybrid approach does the study propose for defect prediction?\",\"answer\":\"The method uses a CNN plus LSTM for feature extraction. It then applies ADASYN to address class imbalance and trains an XGBoost model to predict software defects.\"},{\"question\":\"How was the proposed model evaluated and compared?\",\"answer\":\"The study evaluates the method on five public datasets: CM1, MC1, KC1, PC1, and PC4. Results are compared with state-of-the-art models using metrics such as recall, F1-score, and AUC-ROC.\"}]","HYBRID TECHNIQUE FOR SOFTWARE DEFECT PREDICTION USING MACHINE LEARNING TECHNIQUES | PDF",1785810735,38,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"hybrid-technique-for-software-defect-prediction-using-machine-learning-techniques","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/hybrid-technique-for-software-defect-prediction-using-machine-learning-techniques/122455/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is early software defect prediction important?","Question",{"text":75,"@type":76},"Software defects can trigger system failures, data loss, security vulnerabilities, and financial losses. Early detection reduces runtime reliability problems and technical debt risks.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What hybrid approach does the study propose for defect prediction?",{"text":80,"@type":76},"The method uses a CNN plus LSTM for feature extraction. It then applies ADASYN to address class imbalance and trains an XGBoost model to predict software defects.",{"name":82,"@type":73,"acceptedAnswer":83},"How was the proposed model evaluated and compared?",{"text":84,"@type":76},"The study evaluates the method on five public datasets: CM1, MC1, KC1, PC1, and PC4. Results are compared with state-of-the-art models using metrics such as recall, F1-score, and AUC-ROC.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]