AI-Powered SOC Dashboard Development

I’m building an end-to-end, AI-enabled Security Operations Center dashboard for my MCA final-year project and need an experienced developer to collaborate from prototype to deployment. The core of the work is robust threat detection and analysis—everything else in the stack supports that single goal.

Scope of work
The system will ingest live network traffic, process it in Python, and surface security events through an interactive web interface. XGBoost will drive the risk-prediction engine, though I’m open to complementary models in scikit-learn if they strengthen accuracy. Visual output must rely on clear charts and graphs that let a non-expert spot anomalies at a glance. Flask or FastAPI can anchor the API layer, backed by an SQL store for log retention and incident data. Front-end pieces (HTML, CSS, JavaScript) should feel lightweight yet polished.

Key features to implement
• Threat-detection pipeline tied to XGBoost risk scores
• Real-time traffic monitoring and alerting
• Incident queue with status management (open / triage / resolved)
• Drill-down dashboards with exportable reports (PDF/CSV)
• Admin controls for model retraining, bug fixes, and future scalability

Deliverables & acceptance
1. Source code with clear docstrings and a README that a fellow student can reproduce.
2. A running demo on my VPS or local VM, with deployment notes.
3. Sample report pack demonstrating detected threats, ML prediction rationale, and remediation steps.
4. Final walkthrough session to review code, address bugs, and confirm academic requirements are met.

Please share past projects that blend cybersecurity and ML, note any experience with Flask/FastAPI SOC tooling, and outline an estimated timeline. Budget is flexible; milestones can be split across development, testing, and hand-off.