• Abha Jain

The large and complex software in today’s scenario has led to unavoidable circumstances wherein defects are entering the system at an enormous rate. This has caused an emerging need to assess the severity of these defects considering the shortage of resources due to which equal amount of resources cannot be allocated to all the defects. Thus, in this paper, we intend to propose a model that will be used to assess the severity level of the defect introduced in the system so that defects having higher priority can be dealt with utmost attention. The model is validated against an open source NASA dataset of PITS database using a learning based technique namely Multinominal Multivariate Logistic Regression (MMLR). A series of text mining techniques were applied for pre-processing the data. Finally, validation of the data was conducted using Receiver Operating Characteristics (ROC) characterstics.

Receiver Operating Characteristics, Text mining, Defect, Severity, Multinominal Multivariate Logistic Regression

"Defect Prediction by Analysing Software Project Reports Using Logistic Regression", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.162-168, June-2019, Available :http://www.jetir.org/papers/JETIRCO06032.pdf

"Defect Prediction by Analysing Software Project Reports Using Logistic Regression", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp162-168, June-2019, Available at : http://www.jetir.org/papers/JETIRCO06032.pdf