Project case study

Predictive Vehicle Maintenance System

Applied machine learning workflow for anticipating maintenance needs with experiment tracking and an operator-facing web UI.

Key outcomes

  • Trained and evaluated predictive models for maintenance forecasting.
  • Used MLflow for experiment tracking and model versioning.
  • Built a web UI so predictions were accessible outside notebook workflows.

This project is strong proof of breadth. It shows hands-on machine learning work, but also the operational thinking required to track experiments, compare model performance, and expose results through a usable interface.

It complements the LLM-focused projects by showing that Umar can work across the wider AI and ML delivery spectrum.