Insurance policy register cleaner

The brief

An insurance branch keeps its policies in a spreadsheet full of duplicates, wrong dates and missing premiums. Clean it, document every fix, and summarise the portfolio by product, customer type and region so the branch manager finally has numbers to trust. Good looks like: a cleaning log, totals that reconcile, and a one-page portfolio summary.

What you will build

1. Profile the data: missing values, duplicates, bad dates
2. Clean and document every rule applied
3. Reconcile counts and premiums before and after
4. Summarise the portfolio by product and segment
5. Present the summary in a short report

Free, open data to build it with

• Insurance Company Benchmark (COIL 2000) ↗ UCI Machine Learning Repository

Check each dataset's licence before you publish your work. Your mentor gives your team its own version of the brief (data, scope or region), so every team's project is its own.