| Summary: | In software development, proper risk management is important to achieve project success and reduce possible failures or losses, especially in Agile environments, where traditional approaches usually fail to handle modern projects' dynamic and complex nature. This research proposes a conceptual model to enhance risk management performance by integrating data-driven strategies. The approach uses machine learning, specifically the Decision Tree algorithm, to enhance the risk management process - risk identification, risk assessment, risk mitigation and risk monitoring in software development projects. This research involved two phases in developing the proposed conceptual model: 1) problem assessment and research study and 2) data-driven strategies to enhance risk management performance. Then, the model is evaluated based on its ability to provide accurate and useful information about risk factors such as deadlines for the project, resource allocation, and stakeholder feedback. Besides, gaining expert validation shows the model's effectiveness in real-world software development environments. In conclusion, based on the developed model, we can ensure it will significantly improve the risk management performance in software development. © 2024 IEEE.
|
|---|