100 Best Claude Excel Data Analysis Prompts for Furniture Stores

Direct Answer

The best Claude prompts for Excel data analysis for furniture stores are a curated set of precise, repeatable tasks that transform Excel data into actionable insights for furniture retailers. Use them to analyze sales, inventory, pricing, and customer behavior with clear outputs and constraints. The prompts emphasize actionable results and guardrails to keep analyses grounded in your data, not speculation.

Introduction

This page is a practical prompt library focused on Excel data analysis for furniture stores. It helps analysts quickly generate consistent analyses from Excel datasets covering sales, inventory, pricing, and customer behavior.

Designed for store analysts, category managers, and BI teams, the prompts enable rapid extraction of insights that drive merchandising, operations, and financial decisions.

How to Use These Claude Prompts

• Replace placeholders like [industry], [audience], and [format] with your specifics before running the prompt.
• Add constraints to tailor outputs, such as currency, time ranges, and regional scoping.
• Request outputs in a specific format (CSV, table, or bullet list) to simplify downstream use.
• Verify outputs by cross-checking totals, margins, and key ratios against source data.
• Combine prompts to build end-to-end analyses, from data cleaning to executive-ready summaries.

100 Best Claude Excel Data Analysis Prompts for Furniture Stores

1. Top selling categories: You are a data analyst for a furniture store chain. Task: From an Excel workbook with sheets Sales, Inventory, and Returns, produce a ranked list of top selling furniture categories over the last twelve months. Context: Include category name, total units sold, revenue, average price, and year-over-year growth. Output format: bullet list with category, units, revenue, avg price, YoY%. Constraints: exclude online-only SKUs, treat returns at 0% unless specified, use currency USD, present results in descending order by revenue.
2. Seasonal demand heatmap: Act as a data visualization assistant for a furniture retailer. Given an Excel sheet with Month and Category columns and a numeric sales column, generate a seasonal demand heatmap showing peak months per category for the last two years. Output format: a compact table of categories with peak month and a short interpretation. Constraints: use a single-page summary, color-code high/medium/low with clear labels, avoid charts that require external plugins.
3. Inventory turnover by department: Role: Inventory analyst for a furniture store. Task: Calculate inventory turnover by department using the Inventory and Sales sheets. Provide turnover ratio, average days in stock, and recommended replenishment frequency for the next quarter. Output format: CSV-ready lines with Department, Turnover, Avg Days in Stock, Replenishment Frequency. Constraints: exclude discontinued items, assume cost of goods sold equals current period cost.
4. Price elasticity hints: You are a pricing data specialist. From a dataset with List Price, Discount, and Actual Price, estimate elasticity for the best sellers in the Living Room and Bedroom categories. Output: a short elasticity score per item group, plus 2 recommended pricing actions per group. Output format: a small table and two bullet recommendations. Constraints: use only historical gross margin data from the Excel file.
5. Margin by SKU: As a financial analyst for a furniture retailer, compute gross margin by SKU using Sales and COGS data. Produce a sorted list of top 20 high-margin SKUs with their margin percentage, units sold, and quarter-over-quarter margin change. Output: table with SKU, Margin%, Units Sold, QoQ Margin Change. Constraints: include only active SKUs, ignore bundled SKUs unless explicitly listed.
6. Returns impact snapshot: Act as a returns analytics assistant. From the Returns sheet and Sales sheet, compute return rate by major category and explain which categories contribute most to net loss. Output: a concise summary plus a table of Category, Return Rate, Net Loss Impact. Constraints: only include categories with more than 1,000 units sold in the period.
7. Channel performance split: You are a channel analyst. Split total revenue by Channel (Online, In-Store, Catalogue) using the Sales sheet. Provide channel shares, median order value per channel, and a brief recommendation to optimize mix. Output format: two tables: Channel Share; Channel MVOC. Constraints: ensure consistent currency and exclude tax.
8. Customer lifetime value hints: Role: BI analyst. From Customer data including first purchase date, total spend, and purchases per customer, estimate a simple CLV model for the furniture store. Output: table with Customer Segment, Avg CLV, and recommended retention actions. Constraints: use a 12-month horizon and avoid extrapolation beyond data range.
9. Seasonal promo impact: As a promotions analyst, evaluate the impact of seasonal promotions on unit sales and margin using the Sales and Promotions sheets. Output: short paragraph and a table showing Promotion, Total Units, Avg Price, Margin Impact. Constraints: consider only promotions active for at least two weeks.
10. Best sellers by region: Role: regional analyst. Compare best selling items by Region from Sales by Region data. Output: table with Region, Top Item, Units Sold, Revenue, Margin%. Provide one regional insight perRegion. Constraints: treat ties consistently.
11. SKU rationalization idea: You are a category strategist. From the current SKU list and sales data, identify 5 SKUs for potential rationalization and 5 for potential expansion. Output: two lists with SKU and rationale. Constraints: prefer items with stable demand and high margin.
12. Promotions lift by category: As promotions analyst, quantify lift from promotions by category using pre/post promotion sales data. Output: table with Category, Lift %, Pre, Post, Confidence Note. Constraints: only promotions lasting at least seven days.
13. Stockout risk flags: Role: supply chain analyst. From Inventory and Sales forecasts, flag SKUs at risk of stockouts in next 30 days. Output: list of SKUs with risk score and recommended safety stock level. Constraints: consider seasonality and lead times.
14. A/B test prompts: You are an experimentation specialist. From a dataset of two price variants and unit sales, construct a plan for a controlled A/B test in Excel terms: define hypothesis, metrics, sample size, duration, and decision rule. Output: test plan summary and a mock sheet header for results. Constraints: no external tools.
15. What-if demand forecast: Role: demand planner. Create a what-if scenario in Excel terms: if average monthly demand increases by 10 percent, what is expected annual revenue by category? Output: table with Category, Baseline Revenue, New Revenue, Delta. Constraints: use historical seasonality factors.
16. Seasonality factor table: As a data analyst, build a seasonality factor table for core categories using last 24 months of sales. Output: table with Month, Category, Factor, Rationale. Constraints: factors recalculated monthly.
17. Pricing and stock mix: You are a category analyst. Propose a stock mix adjustment to improve gross margin by 2 percentage points while maintaining service levels. Output: list of SKUs to add or remove with rationale and expected impact. Constraints: assume current stock levels.
18. Customer cohort insights: Role: customer insights analyst. Create cohorts based on first purchase month and analyze repeat purchase rate by cohort over 12 months. Output: table with Cohort, Repeat Rate, Avg Order Value. Constraints: exclude returns from value.
19. Delivery time impact: Act as operations analyst. Correlate delivery lead times with customer satisfaction scores by region. Output: correlation value and a short interpretation; include a table by region. Constraints: use the latest 12 months.
20. Warranty cost proxy: You are a financial planner. Estimate warranty costs as a percentage of revenue by category using historical data. Output: table with Category, Warranty Cost %, Basis, Notes. Constraints: exclude extended warranties.
21. SKU performance drilldown: Role: product analyst. Drill into the top 50 SKUs by revenue to identify drivers of performance. Output: summary and a 5-item drilldown table per SKU with attributes like price tier, margin, promotions, and stock status. Constraints: summarize across major regions.
22. Inventory aging report: As an inventory manager, produce an aging report by days in stock for all SKUs. Output: table with SKU, Days in Stock, Age Bucket, Actionable Next Steps. Constraints: group ages into 0-30, 31-90, 91-180, 181+ days.
23. Fill rate targets: Role: supply chain planner. Calculate fill rate by warehouse and product family. Output: table with Warehouse, Family, Fill Rate, Gap Action. Constraints: seasonal adjustments included.
24. Discount optimization: Pricing analyst task: propose a discount depth by category to reach target revenue while protecting margins. Output: table with Category, Discount %, Expected Revenue, Margin Change. Constraints: apply only on end-user prices.
25. New product viability: Product analyst role. For a list of 6 hypothetical new products, assess viability using projected margin, demand, and fit. Output: table with Product, Projected Margin, Estimated Demand, Viability Score. Constraints: base on historical analogs.
26. Historical trend recap: Data analyst task: summarize 24 months of sales trends by department. Output: concise bullet list of key trends and a 2-column table of Month and Total Revenue. Constraints: exclude outliers.
27. Competitor price alignment: Role: pricing strategist. Compare internal prices to 3 major competitors for similar items. Output: table with Item, Our Price, Comp A, Comp B, Price Gap. Constraints: use consistent currency.
28. Promotional calendar: As a promotions planner, draft a quarterly promotions calendar aligned to seasonality and inventory. Output: table with Quarter, Promotion, Category, Target Revenue, Notes. Constraints: avoid overlapping promotions.
29. Margin by store: Retail analyst task: compute gross margin by store for the last quarter. Output: table with Store, Margin %, Revenue, Margin Change vs prior quarter. Constraints: normalize for store size.
30. Returns by reason: Role: returns analyst. Break down returns by reason (damaged, wrong item, buyer remorse). Output: table with Reason, Count, Return Rate, Cost Impact. Constraints: only legitimate reasons.
31. SKU rationalization deck: Category strategist task: prepare a 1-page rationalization deck for 20 SKUs with rationale and expected impact. Output: structured bullets and a summary table. Constraints: include risks.
32. Shipping cost sensitivity: Logistics analyst: model impact of shipping cost changes on order profitability by region. Output: table with Region, Shp Cost, Profit Impact, Sensitivity. Constraints: use last 12 months.
33. Catalog segmentation: Data scientist: segment catalog by price tier and performance. Output: table with Tier, Avg Price, Revenue, Margin, Units Sold. Constraints: ensure distinct segments.
34. Stock replenishment plan: Supply planner: generate a replenishment plan for the next 8 weeks by SKU, considering lead times and safety stock. Output: list of SKUs with Qty to Order and suggested reorder point. Constraints: min/max constraints.
35. Sales funnel leakage: Marketing data expert: identify where customers drop off in the funnel using Excel data for showroom visits, inquiries, and purchases. Output: table with Stage, Drop-off Rate, Suggested improvement. Constraints: single channel focus.
36. Top customers by spend: BI analyst: list top 100 customers by total spend in the last year, with average order value and purchase frequency. Output: table with Customer ID, Total Spend, AOV, Frequency. Constraints: anonymize identifiers.
37. Returns prevent actions: Operations analyst: propose processes to minimize returns for high-return-rate categories. Output: bullet list with 5 actions and expected effect. Constraints: include operation lead times.
38. Seasonal stock alert: Inventory manager: set up thresholds to alert when stock for seasonal items falls below critical levels. Output: threshold table by category and SKU. Constraints: use safety stock factors.
39. Cross-sell opportunities: Merchandising analyst: identify cross-sell opportunities from purchase data. Output: table with Item, Likely Companion, Expected uplift %, Rationale. Constraints: limit to pairs with at least 50 co-purchases.
40. Customer retention tactics: Customer success role: propose retention actions based on repeat purchase data. Output: list of 6 actions with expected impact and owner. Constraints: tie to promotions or loyalty.
41. Promotion ROI checklist: Audit task: build a checklist to evaluate promotion ROI using a sample dataset. Output: list of 8 checks with quick audit questions. Constraints: applicable to both online and in-store promotions.
42. Inventory safety stock: Supply chain analysis: compute safety stock by SKU using demand variability and lead time. Output: table with SKU, Safety Stock, Service Level. Constraints: assume normal demand.
43. Inventory aging clean-up: Operations task: identify obsolete inventory and propose removal or repurposing. Output: 2 lists: Obsolete and Reusable with rationale. Constraints: include value recovery estimate.
44. SKU gaps map: Merchandising analyst: map gaps where high-potential demand SKUs are missing from current inventory. Output: table with Category, Missing SKU, Rationale, Suggested Action. Constraints: prioritize by potential revenue.
45. Pricing drift monitor: Pricing analyst: monitor price drift across channels for top 30 items. Output: table with Item, Channel, Our Price, Competition Price, Drift Notes. Constraints: update weekly.
46. Wholesale pricing plan: Specialist: develop a wholesale pricing framework for trade customers. Output: table with Tier, Minimum Order, Discount %, Net Revenue Target. Constraints: maintain margin integrity.
47. Gross margin heatmap: BI task: create a gross margin heatmap by department and month. Output: table with Department, Month, Margin%. Constraints: color-coding implied.
48. Forecast accuracy review: Analytics reviewer: compare forecast vs actual for last 6 periods by category. Output: table with Category, Forecast, Actual, Accuracy %, Notes. Constraints: compute accuracy as percentage error.
49. Store performance digest: Regional analyst: produce a digest of store performance with revenue, margin, and stock health by store. Output: table per store with three metrics and overall takeaway. Constraints: filter to active stores.
50. Product mix optimization: Category strategist: propose a product mix change to improve revenue mix by 5 percentage points. Output: list of SKUs to adjust, rationale, expected impact. Constraints: maintain category coverage.
51. Pricing guardrails: Pricing engineer: define guardrails to prevent margin erosion during promotions. Output: table with Scenario, Price Floor, Price Ceiling, Margin Target. Constraints: apply to top 20 items.
52. Channel discount policy: Policy designer: create a consistent discount policy across channels. Output: policy doc outline plus a channel-specific table of discount caps. Constraints: harmonize across channels.
53. SKU performance snapshot: BI analyst: snapshot of top 100 SKUs by revenue with margins and stock status. Output: table with SKU, Revenue, Margin%, Stock Status. Constraints: exclude discontinued.
54. Walkthrough report: Create a step-by-step Excel walkthrough showing how to reproduce key metrics from the dataset. Output: numbered steps and a checklist. Constraints: no external tools.
55. Seasonal impact narrative: Communications role: write a concise narrative explaining seasonal implications for inventory strategy based on data. Output: 5 sentences. Constraints: avoid jargon.
56. Coopetition insights: Strategist task: analyze cross-store collaboration opportunities using shared data. Output: list of 4 ideas with expected benefits. Constraints: preserve data privacy.
57. Demand smoothing plan: Demand planner: propose smoothing actions to reduce volatility in a peak season. Output: table with Action, Expected Smoothing %, Time Horizon. Constraints: tie to promotions.
58. Cash flow impact: Finance task: estimate impact of inventory on cash flow for next quarter. Output: table with Inventory Value, Payable, Cash Conversion Time. Constraints: use accrual basis.
59. SKU health score: Analyst: compute a health score per SKU based on sales velocity, margin, and stockout risk. Output: table with SKU, Health Score, Rationale. Constraints: scale 1-100.
60. Aging outliers: Data cleaning role: identify aging outliers in stock aging data and propose fixes. Output: list of outlier SKUs with suggested actions. Constraints: justify with data.
61. Discount leakage analysis: Audit task: quantify discount leakage by comparing expected discount uptake to actual sales. Output: table with SKU, Discount %, Actual Uptake, Leakage %. Constraints: exclude non-promotional periods.
62. Returns by channel: Returns analyst: break down returns by channel and item family. Output: table with Channel, Family, Return Rate, Cost Impact. Constraints: exclude exchanges.
63. Region growth forecast: Geography analyst: forecast region growth for next quarter based on past 8 quarters. Output: table with Region, Growth %, drivers. Constraints: seasonality factored.
64. Basket analysis: Merchandising task: analyze common item pairs in baskets to suggest cross-sell bundles. Output: table with Pair, Lift %, Confidence, Support. Constraints: require at least 50 occurrences.
65. Delivery experience score: CX role: compute delivery experience score by region using delivery time, damage rate, and satisfaction data. Output: table with Region, Score, Key Driver. Constraints: scale 0-100.
66. Currency exposure: Finance analyst: assess currency exposure if sourcing data in multiple currencies. Output: table with Currency, Exposure %, Mitigation. Constraints: assume two currencies.
67. Product lifecycle plan: Product team: map products to lifecycle stage and propose actions per stage. Output: table with Product, Stage, Action, Timeframe. Constraints: tie to inventory.
68. Store maturation plan: Operations: outline maturation steps for new stores including inventory ramp, staffing, and marketing. Output: checklist and timeline. Constraints: keep it under 6 months.
69. Promotion cadence: Promotions planner: design a cadence that balances volume and margin. Output: 8-week schedule with promotions and expected impact. Constraints: avoid overlap.
70. Brand alignment check: Brand strategist: ensure catalog pricing and visuals align with brand promises. Output: short assessment and 3 actionable fix actions. Constraints: use internal brand guidelines.
71. Aggregation table: Data architecture role: propose an aggregation scheme to summarize sales by grand category and subcategory. Output: table with Category, Subcategory, Revenue. Constraints: avoid cross-category leakage.
72. Data quality score: Data governance: score dataset quality on completeness, consistency, and timing. Output: table with Dimension, Score, Recommendations. Constraints: apply quarterly.
73. Forecast variance drivers: Forecasting analyst: explain major drivers of variance between forecast and actual by category. Output: table with Category, Variance Driver, Impact. Constraints: provide actionable fixes.
74. Scenario comparison: Strategy task: compare three demand scenarios (base, optimistic, pessimistic) for next quarter. Output: table with Scenario, Revenue, Margin, Confidence. Constraints: base scenario uses historical seasonality.
75. Productivity by store: Operations task: measure productivity by store using units sold per employee. Output: table with Store, Units/Employee, Margin. Constraints: exclude new stores.
76. Energy cost impact: Facilities analyst: estimate impact of energy costs on operating margins by region. Output: table with Region, Energy Cost, Margin Impact. Constraints: use latest utility data.
77. Sustainability metrics: Sustainability analyst: track environmental metrics for product sourcing and packaging. Output: table with Metric, Value, Trend. Constraints: avoid proprietary data.
78. Pricing competitiveness: Competitive intelligence: compare our price position vs major retailers for key items. Output: table with Item, Our Price, Avg Competitor Price, Position. Constraints: keep within currency.
79. Damage rate analysis: Quality control: analyze damage rate by supplier and item family. Output: table with Supplier, Family, Damage Rate, Action. Constraints: require sample size.
80. Procurement watchlist: Procurement role: create a watchlist of items at risk of price spikes. Output: table with Item, Supplier, Risk Score, Action. Constraints: weekly update.
81. Sales channel synergy: Channel strategist: identify synergy opportunities between Online and In-Store channels. Output: list of 4 synergies with expected impact. Constraints: measure cross-channel attribution.
82. Loyalty program impact: Loyalty analyst: evaluate how loyalty program affects repeat purchases and average order value. Output: table with Tier, Repeat Rate, AOV, Notes. Constraints: use past 12 months.
83. Lead time by supplier: Sourcing analyst: track supplier lead times and correlate with stockouts. Output: table with Supplier, Avg Lead Time, Stockouts, Recommendations. Constraints: include only active suppliers.
84. Price banding strategy: Pricing strategist: propose price bands to simplify catalog pricing and improve clarity. Output: table with Band, Range, Estimated Margin. Constraints: align with current SKUs.
85. Seasonal markdown plan: Merchandising: craft a markdown plan for seasonal items to clear old stock. Output: table with Item, Markdown %, New Price, Revenue Impact. Constraints: limit to 8 items.
86. Product misfit flags: QA role: flag items that consistently underperform vs category benchmark. Output: table with SKU, Underperformance Reason, Recommendation. Constraints: require 3 months data.
87. SKU standardization: Data governance task: propose standard naming conventions for SKUs and attributes. Output: table with Attribute, Standard, Rationale. Constraints: minimize ambiguity.
88. Workflow automation ideas: Automation engineer: list 6 Excel-based automation ideas to save time and reduce errors. Output: bullet list with brief description and impact. Constraints: no code required.
89. Risk matrix by category: Risk analyst: build a risk matrix for categories based on demand volatility and supplier risk. Output: table with Category, Likelihood, Impact, Mitigation. Constraints: scale 1-5.
90. Data storytelling prompts: Content strategist: craft data stories from the dataset for executive readers. Output: outline with 3 slides and talking points. Constraints: keep it actionable.
91. New store demand check: Expansion analyst: estimate demand for a proposed new store using regional sales data. Output: table with Region, Projected Revenue, Margin. Constraints: assume similar mix.
92. Returns safety guidelines: Operations: draft safety guidelines to handle returns processing efficiently. Output: checklist with 8 items and owners. Constraints: include fraud checks.
93. Product risk appetite: Strategy: define risk appetite per category for product introductions. Output: table with Category, Risk Level, Thresholds. Constraints: align with corporate policy.
94. Data pull plan: Data engineer: design a plan to pull relevant fields from Excel into a dashboard. Output: list of fields, join keys, and refresh cadence. Constraints: avoid sensitive data.
95. Audit trail prompts: Compliance: create prompts to log data changes for key metrics. Output: 6 prompts with purpose and data fields captured. Constraints: maintain privacy.
96. Scenario risk flags: Risk management: tag scenarios with potential downside risks. Output: table with Scenario, Risk Type, Mitigation. Constraints: rate likelihood.
97. Data dictionary entry: Data governance: draft a data dictionary entry for Sales table with fields and definitions. Output: field, type, meaning, example. Constraints: consistent naming.
98. Excel tips for analysts: Training: compile a quick-tip sheet of Excel best practices tailored to furniture retail data. Output: 8 items with brief descriptions. Constraints: practical and actionable.
99. Executive summary prompts: Executive support: generate a concise executive summary from key metrics with 5 bullets. Output: bullets with metric and insight. Constraints: data recency 90 days.
100. Automation risk assessment: Governance: assess risks of automating data processes and propose mitigations. Output: table with Risk, Likelihood, Impact, Mitigation. Constraints: avoid over-automation.

Best Practices

• Keep prompts focused on a single analytic objective to improve accuracy and reproducibility.
• Reuse prompts across stores and time periods to build a consistent data analysis framework.
• Validate outputs by spot-checking a sample of results against the source Excel data.
• Layer prompts with constraints to guard against data leakage, misinterpretation, or missing values.
• Document assumptions and data sources alongside results to support auditable analyses.

Common Mistakes to Avoid

• Using vague goals like analyze sales data without a defined metric or output format.
• Overly broad prompts that require readers to supply missing context or data.
• Ignoring data quality issues or missing values in the analysis prompt outputs.
• Forgetting to specify currency, time frames, or store scope when calculating metrics.
• Relying on outputs without performing a quick validation against raw Excel data.

FAQ

What makes a good Claude prompt for Excel data analysis in furniture retail?

A good prompt clearly defines the data context, objective, output format, constraints, and any validation steps to ensure the result is actionable and rely on verifiable data.

How should I format results for easy use in Excel or dashboards?

Request outputs as CSV lines, tables, or bullet lists with explicit column names to facilitate importing into Excel or dashboards.

Can I reuse prompts across multiple stores or regions?

Yes. Parameterize prompts with placeholders for store, region, or time period so you can reuse them across contexts without rewriting.

What not to include in prompts for furniture data?

Avoid vague objectives, unbounded forecasts, and claims not grounded in your dataset; specify data sources, currency, and time horizons.

How can I ensure data safety when sharing prompts with teams?

Use prompts that reference only non-sensitive fields, anonymize customer identifiers, and document data governance considerations.

Are these prompts compatible with dashboards or BI tools?

Yes. The prompts are designed to produce outputs in table or CSV format that can feed dashboards or BI pipelines.