Claims volume forecast

The brief

A claims department is overwhelmed every monsoon and idle in other months. Forecast monthly claim volumes by line of business, with seasonal and festival effects, so the claims head can plan staff and surveyors ahead. Good looks like: a forecast that beats last year's numbers as a baseline, tested over past seasons, with a staffing plan.

What you will build

1. Build monthly claim series from the data
2. Explore seasonality and weather effects
3. Compare seasonal-naive, ARIMA and Prophet forecasts
4. Back-test over past seasons
5. Turn the forecast into a staffing plan

Free, open data to build it with

• IRDAI handbook and statistics ↗ IRDAI
• Monash Time Series Forecasting Repository ↗ Monash University

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.