Find the few causes behind most of my defects or complaints
A Pareto analysis of defect, complaint, or delay data that shows which few causes to fix first.
The prompt
Run a Pareto analysis on my operational problem data.
Data: [PASTE - e.g. list of defects, complaint reasons, delay codes, downtime reasons, with counts or one row per event]
Period covered: [DATES]
Cost or impact per category, if known: [e.g. rework minutes, refund value]
What I'm trying to improve: [e.g. "reduce returns", "cut downtime"]
Steps:
1. Clean the categories: merge duplicates and near-duplicates (e.g. "late", "delayed", "LATE DELIVERY"), and list what you merged so I can check.
2. Build a table: category | count | % of total | cumulative %.
3. Do a second ranking by impact (cost or time) if I gave it - the most frequent problem isn't always the most expensive.
4. Identify the "vital few" that make up roughly 80% of the total, and say plainly if the data doesn't show a strong 80/20 pattern.
5. Flag data quality problems: vague categories like "other" or "misc" that are too large, missing values, or a short period that may not be representative.
6. For the top 3 categories, suggest likely root causes to investigate (as hypotheses, not conclusions) and what extra data would confirm them.
Describe the chart I should build (bars sorted descending plus cumulative line). Use only my numbers; don't estimate missing values.
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
- DATES
- e.g. rework minutes, refund value
- e.g. "reduce returns", "cut downtime"
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.