Machine learning project for modeling UFC fight outcomes with Elo-based ratings. Project scope, requirements, and deliverables are defined in docs/scoping.md. src/data/cleaning.py cleans the raw fight- and round-level CSVs (missing values, dtypes), src/data/splitting.py splits fights chronologically for training, and src/features/engineering.py builds leakage-safe matchup and fighter-history features - everything is computed from data known before the fight being predicted. EDA lives in notebooks/ (eda.ipynb, univariatequestions.ipynb, bivariatequestions.ipynb, multivariatequestions.ipynb), including a documented red-corner recording bias in the source data that any model built on this…