INTERPRETABLE ACCURACY OF SOFTWARE DEFECT PREDICTION USING MACHINE LEARNING TECHNIQUE
Volume: 13 - Issue: 07 - Date: 29-07-2024
Approved ISSN: 2278-1412
Published Id: IJAECESTU410 | Page No.: 101-105
Author: Monika Nagar
Co- Author: Dr. Indu Shrivastava, Swati Khanve,Dr. Sneha Soni,
Abstract:-- The presence of software defects can lead to substantial impacts in terms of the functionality, reliability, and
overall effectiveness of software systems. The identification and elimination of defects during the initial phases of
software develo pment are of the highest priority in ensuring the availability of software products of superior quality. The
software defect prediction is to predict the defects in historical data base. So, in real world, it is difficult to predict
because it requires more number of data variables, metrics and historical data. The ML concentrates on the algorithms
entirely centered on statistical methods and data mining techniques for classifying and predicting the defects and these
statistical methods followed are quite similar to regression based methods which we used earlier to the ML. The RF ML
technique is providing good accuracy compared to other LR and SVM technique. In this model is simulated python
language and calculated simulation parameter i.e. precision, recall and accuracy
Key Words:-- Software Defects, Accuracy, Precision, Recall, Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM)
Area:-Engineering
DOI Member: 135.66.411
DOI Member:
Preview This Article
