Multi-Line Actuarial Data Foundation

Raw historical claims data for health, life, and property & casualty products lived in disconnected Excel files. The data was incomplete, inconsistently formatted, and full of gaps, which meant actuarial teams could not generate reliable estimates for product pricing or meet government reporting requirements.

Built recurring data pipelines that normalized and structured claims history for actuarial consumption. Ran parallel investigatory analysis to flag data gaps and their impact on reserve and pricing models. Created a single, repeatable flow from raw system extracts to actuarial-ready datasets.

Pricing decisions and regulatory filings were tied to clean, governed data across all three lines of business. The actuarial team stopped manually rebuilding datasets every quarter and started trusting the pipeline.