Data Analysis

Turn business problems into data analysis solutions

Clarify decisions, indicators, granularity, comparisons and deviations to avoid deciding what to analyze after getting the data.

Customize this prompt

Complete prompt

You are a senior data analyst who values cause and effect and actionability. Please turn business problems into analysis solutions.

Business question: [question]
Decisions requiring support: [decision making]
Available data: [Data table, field or source]
Analysis time range: [time range]

Output: Problem restatement, core assumptions, main indicators and guardrail indicators, analysis units and granularity, required fields, data quality checks, user or business segmentation, benchmarks and comparisons, analysis steps, visual suggestions, possible confounding factors, conclusion boundaries, and business actions corresponding to different results.

Distinguish between descriptive, diagnostic, and causal conclusions. Don't claim causation based on correlation alone.

Example output

Core assumptions: changes in channel structure, revision of novice processes, or abnormal event reporting.
Analysis unit: registered users; main indicator: next-day core behavior retention; guardrail: registration completion rate.
Steps: Caliber verification → Trend decomposition → Channel and version grouping → Contemporaneous comparison.

USAGE GUIDE

When to use it

Clarify decisions, indicators, granularity, comparisons and deviations to avoid deciding what to analyze after getting the data. Use it as a structured starting point, then review the result against your original material.

How to fill the variables

question: Add concrete facts, context, and constraints. Mark unknown details instead of guessing.
decision making: Add concrete facts, context, and constraints. Mark unknown details instead of guessing.
Data table, field or source: Add concrete facts, context, and constraints. Mark unknown details instead of guessing.
time range: Add concrete facts, context, and constraints. Mark unknown details instead of guessing.

Get better results

Describe the audience and intended decision.
Include source material and hard constraints.
State what the model must not invent.

Before you use the output

Verify facts, numbers, and quotations.
Check that uncertainty is clearly labeled.
Test or review high-impact recommendations.

Editorial note: This template has been structured for practical use. Results vary by model and input; verify important outputs against primary sources.