• M. Ayesha Ziana
• Dr. Charles J

Agile software development methodology has encouraged the application of various tools that mitigate the risks of the software project as much as possible. In spite of this, the risk analysis process in Agile software projects usually follows an implicit path without the use of explicit and structured methods. In short, explicit risk analysis methodologies are scarce in Agile software development. To perform a structured risk mitigation activity, it is essential to analyze the risks. The application of machine learning to risk assessment activities is growing. This motivated us to perform this study, which illustrates the significance of machine learning in the risk assessment process, particularly in the risk analysis phase. This study, apart from exhibiting the results of the implemented machine learning algorithms in the literature, serves as a starting point in developing our own risk analysis model by predicting the impacts of the risks identified, in terms of project performance goals and the level of negative impacts created. A survey has been planned as a continuation of this process in order to finalize the dataset with the required features to be given as inputs for our machine learning model in the future.

Agile software development methodology has encouraged the application of various tools that mitigate the risks of the software project as much as possible. In spite of this, the risk analysis process in Agile software projects usually follows an implicit path without the use of explicit and structured methods. In short, explicit risk analysis methodologies are scarce in Agile software development. To perform a structured risk mitigation activity, it is essential to analyze the risks. The application of machine learning to risk assessment activities is growing. This motivated us to perform this study, which illustrates the significance of machine learning in the risk assessment process, particularly in the risk analysis phase. This study, apart from exhibiting the results of the implemented machine learning algorithms in the literature, serves as a starting point in developing our own risk analysis model by predicting the impacts of the risks identified, in terms of project performance goals and the level of negative impacts created. A survey has been planned as a continuation of this process in order to finalize the dataset with the required features to be given as inputs for our machine learning model in the future.

"SIGNIFICANCE OF MACHINE LEARNING IN RISK IMPACT ANALYSIS FOR AGILE SOFTWARE ENTERPRISES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 6, page no.99-103, June-2023, Available :http://www.jetir.org/papers/JETIRFZ06017.pdf

"SIGNIFICANCE OF MACHINE LEARNING IN RISK IMPACT ANALYSIS FOR AGILE SOFTWARE ENTERPRISES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 6, page no. pp99-103, June-2023, Available at : http://www.jetir.org/papers/JETIRFZ06017.pdf