[
  {
    "id": "10.1007/978-3-030-81462-5_29",
    "type": "paper-conference",
    "title": "An Ensemble Learning Approach for Software Defect Prediction in Developing Quality Software Product",
    "author": [
      {
        "family": "Saheed",
        "given": "Yakub Kayode"
      },
      {
        "family": "Longe",
        "given": "Olumide"
      },
      {
        "family": "Baba",
        "given": "Usman Ahmad"
      },
      {
        "family": "Rakshit",
        "given": "Sandip"
      },
      {
        "family": "Vajjhala",
        "given": "Narasimha Rao"
      }
    ],
    "editor": [
      {
        "literal": "Mayank Singh"
      },
      {
        "literal": "Vipin Tyagi"
      },
      {
        "literal": "P. K. Gupta"
      },
      {
        "literal": "Jan Flusser"
      },
      {
        "literal": "Tuncer Ören"
      },
      {
        "literal": "V. R. Sonawane"
      }
    ],
    "container-title": "Advances in Computing and Data Sciences: 5th International Conference, ICACDS 2021, Nashik, India, April 23–24, 2021, Revised Selected Papers, Part I",
    "collection-title": "Communications in Computer and Information Science",
    "issued": {
      "date-parts": [
        [
          2021,
          10,
          23
        ]
      ]
    },
    "volume": "1440",
    "page": "317-326",
    "publisher": "Springer International Publishing",
    "ISSN": "1865-0929",
    "ISBN": "9783030814625",
    "DOI": "10.1007/978-3-030-81462-5_29",
    "URL": "https://www.narasimharao.net/research/ensemble-learning-software-defect-prediction/",
    "abstract": "Software Defect Prediction (SDP) is a major research field in the software development life cycle. The accurate SDP would assist software developers and engineers in developing a reliable software product. Several machine learning techniques for SDP have been reported in the literature. Most of these studies suffered in terms of prediction accuracy and other performance metrics. Many of these studies focus only on accuracy and this is not enough in measuring the performance of SDP. In this research, we propose a seven-ensemble machine learning model for SDP. The Cat boost, Light Gradient Boosting Machine (LGBM), Extreme Gradient Boosting (XgBoost), boosted cat boost, bagged logistic regression, boosted LGBM, and boosted XgBoost were used for the experimental analysis. We also used the separate individual base model of logistic regression for the analysis on six datasets. This paper extends the performance metrics from only the accuracy, the Area Under Curve (AUC), precision, recall, F-measure, and Matthew Correlation Coefficient (MCC) were used as performance metrics. The results obtained showed that the proposed ensemble Cat boost model gave an outstanding performance for all the three defects datasets as a result of being able to decrease overfitting and reduce the training time.",
    "keyword": "Software defect prediction, Software product, Cat boost, Light gradient boosting machine, NASA repository, Extreme gradient boosting, Area under curve, F-measure, software defect prediction, ensemble learning, CatBoost, LightGBM, XGBoost, gradient boosting, bagging and boosting, software quality, NASA defect datasets, Matthews correlation coefficient, machine learning evaluation metrics, software engineering",
    "language": "en"
  }
]