Project context
As Data Lead on an MxV Rail team project from August through December 2025, I used Python and Orange to analyze months of train-run data and shape the analytical story presented to the team.
How I structured the analysis
- Organized observations into comparable views by rail car, operating condition, and track segment.
- Reviewed repeated runs to distinguish recurring behavioral differences from isolated observations.
- Built comparative visual material that made condition- and segment-level variation easier to inspect.
- Translated the analysis into focused discussion points for maintenance scheduling and safety review.
Patterns surfaced
The analysis highlighted where rail-car behavior varied across operating conditions and track sections, giving the team a clearer basis for deciding which combinations warranted follow-up review.
Private-data note
The underlying operational dataset and code cannot be published. This case study therefore focuses on the analytical structure, comparisons, and communication deliverables that can be described publicly.