Data Analysis Prompts

Analyse this budget data comparing actual spend versus budgeted amounts. For each line item: (1) Calculate the variance (actual minus budget) and variance percentage, (2) Flag any variances greater than 10% as significant, (3) Categorise variances as Favourable or Unfavourable, (4) Suggest possible reasons for the top 5 largest variances, (5) Provide a summary with total budget utilisation percentage. Format as a table with colour-coded indicators.

Analyse for correlations between [VARIABLES]. For each significant one: (1) State the relationship, (2) Strength, (3) Direction, (4) Possible explanations, (5) Caveats. Create a correlation matrix.

Define metrics for a [PURPOSE] dashboard. For each metric: name, definition, data source, calculation, target, frequency, owner, and why it matters. Limit to 8-10 KPIs.

Create a data cleaning plan for [DATASET]. Check for: duplicates, missing values, inconsistent formats, outliers, invalid entries, and typos. Prioritise fixes by impact on analysis.

Help me clean up this messy spreadsheet data. The issues I am seeing: [DESCRIBE PROBLEMS — duplicates, inconsistent formatting, missing values, merged cells, etc.]. Provide a step-by-step cleanup plan: (1) Remove Duplicates — how to identify and remove them, (2) Standardise Formats — fix date formats, number formats, text capitalisation, (3) Handle Missing Data — strategy for blank cells (fill, flag, or remove), (4) Split/Merge Columns — separate combined data into proper columns, (5) Validate Data — formulas to check for errors and outliers, (6) Final Structure — what the clean dataset should look like. Provide the exact Excel steps or formulas for each action.

Analyse this employee headcount data and provide: (1) Total headcount by department and location, (2) Hiring trends — new joiners per month over the past year, (3) Attrition analysis — leavers by department, tenure, and reason if available, (4) Diversity breakdown — gender, age bands, and tenure distribution, (5) Cost analysis — average salary by department and level, (6) Recommendations — flag departments with high attrition or understaffing risks. Present as a combination of tables and key insight bullets.

Analyse this data and identify: (1) The top 3 trends over the time period shown, (2) Any anomalies or outliers that stand out, (3) A comparison between the highest and lowest performing categories, (4) A brief recommendation based on the patterns. Present your findings with specific numbers and percentages. Use a clear, executive-summary style.

I need an Excel formula to [DESCRIBE WHAT YOU WANT TO CALCULATE]. My data is structured as: [DESCRIBE YOUR COLUMNS/LAYOUT]. Please provide: (1) The exact formula I should use, (2) A step-by-step explanation of how the formula works, (3) Where to place it in my spreadsheet, (4) Any helper columns needed, (5) Common errors to watch for, (6) An alternative formula approach if there is one. If the task is complex, break it into multiple simpler formulas rather than one giant nested formula.

Analyse this expense data and provide: (1) Total Spend Summary — by category, department, and time period, (2) Top Spenders — individuals or departments with highest expenses, (3) Trend Analysis — month-over-month spending patterns, (4) Anomaly Detection — flag any expenses that seem unusual (unusually high amounts, weekend expenses, duplicate claims), (5) Policy Compliance — identify expenses that may violate common corporate policies (excessive meals, unapproved travel class), (6) Cost-Saving Opportunities — 3-5 specific recommendations to reduce spending, (7) Benchmarks — compare against typical corporate spending ratios. Format as a clear report with tables.

Using this data, create a KPI dashboard summary. For each metric: (1) Current value, (2) Target value, (3) Variance from target as a percentage, (4) RAG status (Red if >10% below target, Amber if 5-10% below, Green if on or above target), (5) Trend direction compared to last period (↑ improving, → stable, ↓ declining). Present as a clean table. Then provide a narrative summary of the top 3 areas needing attention and top 3 areas performing well.

Analyse this data using a pivot approach. Group by [DIMENSION], measure [METRIC]. Show: totals, averages, percentages, and identify the top and bottom performers. Add a chart.

Analyse this sales pipeline data and provide: (1) Total pipeline value by stage (Prospect, Qualified, Proposal, Negotiation, Closed Won/Lost), (2) Win rate by stage and by sales rep, (3) Average deal cycle time from first contact to close, (4) At-risk deals — opportunities that have been in the same stage for more than [X] days, (5) Revenue forecast for the next quarter based on current pipeline and historical win rates, (6) Top 5 recommendations to improve pipeline conversion.

Analyse these survey results. Provide: (1) Response rate and validity, (2) Key quantitative findings, (3) Open-ended theme analysis, (4) Segments that differ significantly, (5) Top 3 actionable insights, (6) Follow-up recommendations.

Create a what-if scenario analysis for [DECISION/PROJECTION]. Build three scenarios: (1) Optimistic — best case with favourable assumptions, (2) Realistic — most likely case based on current trends, (3) Pessimistic — worst case with unfavourable assumptions. For each scenario provide: variable assumptions used, projected outcome (revenue, cost, timeline, or metric), probability estimate, key risks, and recommended actions. Create a comparison table and identify the break-even point or decision threshold. Conclude with a recommendation on which scenario to plan for.