Paper Title
Software Bug Classification using Machine Learning

Abstract
The manualapproachofbugreportsto detectiontechnicallyexpert teams is atime-consuming and much expensive method. Automated Machine Learning (ML) methods are reliable when it comes to finding solution less knowledge. In most instances, software domain difficulties are defined as a learning experience that varies depending on the scenario and changes appropriately. A statistical model is generated using a machine learning technique and separated into non-defective modules. Developers may use machine learning models to obtain relevant information after categorization and analyzing data from various sources. Machine learning techniques have been proved to be effective in finding software problems. It uses several machine learning algorithms; this study employed publicly accessible data sets to classify software bugs. It provided a comparative output analysis of the various machine learning approaches for software bug prediction. Results demonstrate each machine learning outcome with classification accuracy and F-measure of each algorithm with real time twitter dataset. Keywords - Deep Leaning, Machine Learning, Bug Classification, NLP, Feature Extraction, Feature Selection, Report Generation, Overflow Attacks