Analyze loss ratio and combined ratio trends by line of business
A breakdown of what is driving underwriting results, separating frequency, severity, rate, mix, and development effects.
The prompt
Help me analyze underwriting performance for our insurance book.
Data: [PASTE or describe - earned premium, incurred losses (paid + case + IBNR), loss adjustment expense, underwriting expense, claim counts, exposures, by line/segment and accident or calendar year]
Basis: [accident year or calendar year; net or gross of reinsurance]
Lines or segments: [LIST]
Known events: [catastrophes, rate changes, underwriting guideline changes, reserve strengthening]
Question I need answered: [e.g. "why did our auto combined ratio rise 6 points?"]
Do this:
1. Calculate loss ratio, LAE ratio, expense ratio, and combined ratio by line and year. Show formulas.
2. Decompose changes into frequency (claims per exposure) and severity (average cost per claim), and estimate how much rate change, mix shift, and catastrophe losses contributed.
3. Separate calendar-year effects of prior-year reserve development from current accident-year performance.
4. Flag segments where loss trend is outrunning rate.
5. Note data limitations - immature accident years, IBNR uncertainty, small credibility in thin segments.
Output:
- A summary table by line.
- The top 3-5 drivers, ranked by impact in ratio points.
- 3 actions to investigate (e.g. rate filing, underwriting guideline change, claims process review).
Use only my data; do not assume industry benchmarks unless I provide them. Reserve conclusions should be confirmed by our actuaries.
Highlighted [brackets] are blanks to replace with your own details.
Fill in the blanks and use this promptMore Data & Analysis prompts
What to fill in
- accident year or calendar year; net or gross of reinsurance
- LIST
- e.g. "why did our auto combined ratio rise 6 points?"
How this prompt is built
This prompt follows the Few-Shot structure (Few-shot prompting). A few-shot prompt includes one or more worked examples of the input and the output you want, so the model can copy the pattern instead of guessing it.
Related prompts
- Identify the leading and lagging indicators for my business or teamSorts your metrics into leading and lagging indicators, links each lead to the outcome it predicts, and fills gaps in early-warning measures.
- Pick the three insights and five numbers my executives needRanks your findings down to the single most important insight, the top three, the five numbers to watch, and the biggest surprise.
- Break down why a number changed between two periodsA driver breakdown and bridge that shows exactly which segments, volume, price, or mix effects caused a metric to move.
- Check whether my data shows causation or just correlationSeparates trend, correlation, and possible causation in your analysis and gives you the strongest claim you can honestly make.