Problem: IT projects often fail due to unforeseen risks, leading to budget overruns and delays.
Outcome: Build an AI model that predicts risks in IT projects based on historical data.
Week 1-2: Literature Review & Data Collection
Study IT project risk factors.
Gather historical project data from IT firms or repositories.
Week 3-4: Feature Engineering & Model Selection
Identify key features influencing project risk.
Select suitable AI/ML models for risk prediction.
Week 5-6: Model Training & Testing
Train AI model using past project data.
Test accuracy with different datasets.
Week 7-8: Integration with Project Management Tools
Develop a prototype dashboard.
Integrate with PM tools like Jira, Trello.
Week 9-10: Validation & Risk Mitigation Strategy
Validate model with real project data.
Develop risk mitigation recommendations.
Week 11-12: Report & Final Presentation
Document findings and improvements.
Present to IT project managers.
