100 Best Claude Excel Data Analysis Prompts for Airbnb Hosts

Direct Answer

The best Claude prompts for Excel data analysis for Airbnb hosts are a curated set of actionable, Excel-ready prompts that cover revenue, occupancy, pricing, and guest experience. Each prompt is designed to yield structured outputs, with placeholders and constraints to fit real-world Airbnb data, enabling faster, data-driven decisions.

Introduction

This page is a practical prompt library for Excel data analysis tailored to Airbnb hosts. It provides 100 Claude prompts that help you analyze revenue, occupancy, pricing, and guest experience using Excel.

Designed for Airbnb hosts, property managers, and short-term rental operators, the prompts help translate your data into actionable insights and dashboards.

How to Use These Claude Prompts

• Replace placeholders such as [listing_id], [season], [date], and [ADR] with your actual data in Excel-compatible tables.
• Add constraints to force outputs in USD, two-decimal currency, or a specific date range as needed.
• Request outputs in formats that are ready to paste into Excel, such as CSV-ready tables or pivot-table layouts.
• Verify outputs by cross-checking totals, ensuring no data gaps, and validating calculations against known benchmarks.
• Reuse prompts by adjusting the scope to a single listing or the full portfolio, and save as templates for recurring analysis.
• If outputs include charts or dashboards, ensure data ranges are correct and refreshable in Excel or any compatible spreadsheet tool.

100 Best Claude Excel Data Analysis Prompts for Airbnb Hosts

1. Revenue by listing: You are an analytic assistant. Task: analyze revenue across all Airbnb listings for a given property portfolio. Context: use Excel-compatible tables with columns: listing_id, nightly_rate, nights_booked, cleaning_fee, occupancy_days, platform_fee, tax. Output: provide a summary table of revenue by listing, then a chart-ready CSV of revenue per listing, and a short interpretation in 2 bullet points. Constraints: exclude canceled nights, include seasonal adjustments if data shows, present figures in USD, no more than three decimal places.
2. Occupancy heatmap setup: You are a data analyst. Task: generate a plan to create an occupancy heatmap for the last 12 months across all listings. Context: data includes date, listing_id, nights_booked, occupancy_rate. Output: a step-by-step Excel-ready guide, a formulas list, and a sample pivot table layout. Constraints: use conditional formatting rules to highlight high and low occupancy, include a one-page checklist, and deliver in a .xlsx-ready description.
3. Pricing impact analysis: You are a pricing analyst. Task: quantify how nightly rate adjustments affect occupancy and gross revenue. Context: data fields nightly_rate, nights_booked, occupancy_rate, revenue. Output: a regression-ready model statement in plain text, plus a table of top 5 price points and projected monthly revenue. Constraints: assume a fixed demand curve, compute elasticity estimates, provide interpretation in non-technical language.
4. Seasonality decomposition: You are a data scientist. Task: decompose monthly occupancy and revenue into trend, seasonality, and residual components. Context: columns include month, year, occupancy_rate, revenue, listing_id. Output: provide a seasonal index table, a chart-ready summary, and a brief interpretation. Constraints: use additive decomposition, ensure total equals observed values.
5. Cost per booking: You are an operations analyst. Task: calculate cost per booked night including hosting platform fees and cleaning. Context: data: nightly_rate, platform_fee, cleaning_fee, nights_booked, occupancy_days. Output: a daily cost per booking table by listing, plus a one-line takeaway for each listing. Constraints: present in USD, exclude refunds, rounded to two decimals.
6. Cash flow projection: You are a financial analyst. Task: build a 12-month cash flow projection for the portfolio using historical trends. Context: inputs: historical revenue, expenses, taxes, seasonality. Output: a month-by-month cash balance forecast in a table and a brief narrative for the CEO. Constraints: use conservative assumptions, include a sensitivity scenario for a 10 percent occupancy drop.
7. ADR benchmarking: You are a benchmarking analyst. Task: compare average daily rate (ADR) across listings against a market benchmark. Context: data: ADR per listing, market ADR, occupancy. Output: a comparison table with gaps and a 2-sentence recommended actions. Constraints: normalize by listing_type and season.
8. Occupancy drivers list: You are a data analyst. Task: identify top factors driving occupancy for the portfolio. Context: data: amenities, location, occupancy_rate, nights_booked, reviews_count. Output: ranked list of drivers with brief rationale and Excel-ready data filters. Constraints: include at least five drivers and a one-sentence action per driver.
9. Guest experience index: You are a customer insights analyst. Task: create a guest experience index from survey responses and review sentiment. Context: fields: guest_rating, review_sentiment_score, response_time, inquiries_resolved. Output: index score by listing and a 1-page dashboard layout for Excel. Constraints: scale 0-100, higher is better, include interpretation notes.
10. Cancellation impact analysis: You are a revenue analyst. Task: quantify how cancellation rate affects revenue. Context: data: cancellations, nights_booked, refund_amount, revenue. Output: a sensitivity table showing revenue under three cancellation scenarios and a one-page executive summary.
11. Booking window trends: You are a data analyst. Task: analyze booking window (days between booking and stay) trends. Context: fields: listing_id, booking_date, stay_date, nights_booked. Output: distribution histogram, summary stats, and two strategic recommendations. Constraints: provide Excel-ready instructions.
12. Cutover risk checklist: You are a risk analyst. Task: develop a data-driven risk checklist for seasonal price changes. Context: data: occupancy_rate, ADR, occupancy_history. Output: a ranked risk checklist with thresholds and contingency actions for Excel.
13. Cancellation reason map: You are a data mapping analyst. Task: map cancellation reasons to impact on revenue. Context: fields: listing_id, cancellation_reason, revenue_loss, booking_id. Output: a categorized reasons table and a 1-page heatmap suggestion. Constraints: include top three reasons with estimated revenue impact.
14. Refund vs. retention: You are a retention analyst. Task: compare revenue impact of refunds versus retention strategies. Context: data: refunds, net_revenue, occupancy. Output: two scenario comparisons with a recommended approach in plain language.
15. Top performing listings: You are a portfolio analyst. Task: rank listings by revenue per available night (RevPAN). Context: fields: listing_id, revenue, available_nights. Output: top 5 and bottom 5 with short summaries and Excel-ready formulas for RevPAN.
16. Market demand snapshot: You are a market analyst. Task: produce a quarterly demand snapshot for the target city. Context: data: quarter, occupancy, ADR, revenue. Output: a concise table and 2 recommended actions for growth.
17. Competitor pricing map: You are a competitive intelligence analyst. Task: map competitor nightly rates by day of week. Context: data: day_of_week, competitor_rate, market_rate. Output: a mapped plan with a chart-ready dataset and 2 insights.
18. Length of stay trends: You are a data analyst. Task: analyze length of stay (LOS) patterns across listings. Context: data: stay_length, nights_booked, listing_id. Output: LOS distribution and 2 optimization ideas.
19. Cancellation forecasting: You are a forecasting analyst. Task: forecast cancellations for next 30 days. Context: historical_cancellations, seasonality, listings. Output: forecast table, accuracy note, and a contingency plan.
20. Occupancy by weekday: You are a data analyst. Task: determine occupancy by day of week across listings. Context: data: listing_id, weekday, nights_booked. Output: a pivot-ready occupancy by weekday table and 2 actionable optimizations.
21. Dynamic pricing prompts: You are a pricing engineer. Task: craft dynamic pricing prompts for Excel using historical ADR and occupancy. Context: fields: ADR, occupancy, date. Output: a template for price adjustment prompts and a checklist for validation.
22. Guest turnover cost: You are an operations analyst. Task: estimate turnover cost per guest. Context: data: cleaning_fee, turnover_time, staff_costs, bookings. Output: cost per turnover with breakdown and a rerunable calculator.
23. Revenue by listing type: You are a financial analyst. Task: split revenue by listing type (entire home, private room). Context: revenue_by_type, listings. Output: comparative table and 2 marketing tips based on findings.
24. Tax impact calculator: You are a tax advisor. Task: estimate quarterly tax liability from Airbnb income. Context: revenue, deductible_expenses, tax_rate. Output: a tax projection table with notes and a CSV-ready export.
25. Occupancy forecast dashboard: You are a dashboard designer. Task: design an Excel dashboard plan for occupancy forecast. Context: metrics: occupancy_rate, nights_booked, listings. Output: layout blueprint and required data tables with sample formulas.
26. Review sentiment scan: You are a sentiment analyst. Task: scan reviews for sentiment and key themes. Context: review_text, rating, date. Output: sentiment score by listing and 3 themes with example quotes.
27. Arrival experience metrics: You are a guest experience analyst. Task: quantify arrival experience impact on ratings. Context: data: checkin_time, welcome_notes, guest_rating. Output: correlation findings and improvement plan.
28. Pricing salt bands: You are a pricing specialist. Task: define pricing bands based on occupancy and seasonality. Context: data: occupancy_rate, season, ADR. Output: bands with suggested price ranges and trigger points.
29. Promotions impact test: You are an promotions analyst. Task: evaluate effectiveness of price promotions. Context: data: promo_flag, revenue, bookings, ADR. Output: uplift analysis and recommended promotion calendar.
30. Seasonal occupancy map: You are a data mapper. Task: create a seasonal occupancy map by month. Context: data: month, occupancy_rate, listings. Output: a color-coded map plan and a summary of peak months.
31. Cleaning cost optimization: You are an operations analyst. Task: optimize cleaning costs without affecting guest experience. Context: data: cleaning_costs, turnover_time, ratings. Output: cost-saving ideas with impact estimates.
32. Minimum night policy impact: You are a policy analyst. Task: assess impact of minimum stay changes. Context: data: min_nights, occupancy, revenue. Output: impact table and recommended policy range.
33. Discount strategy guide: You are a pricing strategist. Task: craft discount strategies by season. Context: data: season, occupancy, ADR. Output: discount tiers and validation checks in Excel.
34. Guest origin trends: You are a market analyst. Task: analyze guest origin distribution. Context: data: country, bookings, revenue. Output: origin dashboard plan and 2 localization ideas.
35. Review response plan: You are a customer service analyst. Task: create a standard review response strategy. Context: reviews, ratings, response_time. Output: a response playbook with 10 templates and customization tips.
36. Inventory utilization: You are an operations analytics lead. Task: measure listing inventory utilization. Context: data: available_nights, booked_nights, listings. Output: utilization rate by listing and a packing list of actions.
37. Ranking by guest rating: You are a data analyst. Task: rank listings by guest rating adjusted for response time. Context: data: rating, response_time, listings. Output: top 5 and bottom 5 with notes.
38. Data validation rules: You are a data quality engineer. Task: define Excel data validation rules for Airbnb metrics. Context: fields: date, listing_id, ADR, occupancy. Output: a validation plan and sample formulas.
39. Forecast accuracy check: You are a forecasting analyst. Task: calculate backtesting accuracy for occupancy forecast. Context: actuals, forecasts, horizon. Output: accuracy metrics and a 1-page improvement plan.
40. Competitor review scraping plan: You are a competitive intelligence analyst. Task: plan compliant review scraping for pricing insights. Context: data: listings, rates, reviews. Output: scraping plan, data schema, and a risk note.
41. Nightly rate elasticity: You are a pricing scientist. Task: estimate rate elasticity using historical data. Context: ADR, occupancy, revenue. Output: elasticity coefficient and action suggestions.
42. Seasonal risk matrix: You are a risk analyst. Task: build a seasonal risk matrix for occupancy and revenue. Context: data: month, occupancy, ADR. Output: matrix with risk scores and mitigations.
43. Guest messaging timing: You are a communications analyst. Task: optimize guest messaging timing before check-in. Context: check_in_time, response_time, guest_satisfaction. Output: timing plan and 2 template messages.
44. Refund policy impact: You are a policy analyst. Task: model impact of refund policy on occupancy and revenue. Context: policy, bookings, revenue. Output: scenarios and recommended policy stance.
45. Occupancy by seasonality: You are a data analyst. Task: break down occupancy by season and season length. Context: data: season, occupancy_rate, listing_id. Output: seasonality report and actionable tips.
46. Booking channel mix: You are a channel analyst. Task: analyze bookings by channel (direct, OTA). Context: data: channel, revenue, nights_booked. Output: channel share table and 2 optimization ideas.
47. Pacing vs target: You are a performance analyst. Task: compare booking pace to targets. Context: dates, bookings, target_pace. Output: variance report and corrective actions.
48. Guest demographics: You are a market researcher. Task: profile guest demographics from bookings. Context: age_group, country, bookings. Output: demographic summary and 2 segmentation actions.
49. Rate parity check: You are a pricing analyst. Task: verify rate parity across platforms. Context: listing_id, rate, platform. Output: parity report with violations and fixes.
50. Promotional calendar: You are a marketing analyst. Task: build an Excel-ready promotional calendar aligned to occupancy. Context: dates, promotions, expected impact. Output: calendar plan and validation checks.
51. Late checkout impact: You are a operations analyst. Task: assess impact of late checkout on turnover. Context: checkout_time, turnover_time, guest_rating. Output: occupancy impact and cost implications.
52. Guest sentiment drift: You are a sentiment analyst. Task: detect drift in guest sentiment over time. Context: date, sentiment_score, listing_id. Output: drift report and intervention suggestions.
53. Occupancy by neighborhood: You are a market analyst. Task: compare occupancy across neighborhoods. Context: listing_id, neighborhood, occupancy_rate. Output: neighborhood ranking and 2 targeted actions.
54. Excel template blueprint: You are a data architect. Task: design an Excel workbook blueprint for Airbnb analytics. Context: metrics, sheets, data models. Output: sheet list with data sourcing and formulas.
55. Booking horizon banding: You are a pricing analyst. Task: create booking horizon bands (short, mid, long). Context: data: days_to_stay, bookings. Output: bands with recommended pricing rules.
56. Inventory risk alerts: You are a data quality analyst. Task: set up Excel-based risk alerts for inventory. Context: thresholds, occupancy, bookings. Output: alert rules and a sample alert message.
57. Revenue per listing: You are a financial analyst. Task: compute revenue per listing with variance by month. Context: listing_id, month, revenue. Output: table and 2 trend insights.
58. Penalty risk analysis: You are a risk manager. Task: assess risk of penalties from overbooking. Context: bookings, available_nights, penalties. Output: risk rating and mitigation steps.
59. Check-in turnout rate: You are a operations analyst. Task: measure check-in turnout vs expected arrivals. Context: booked_guests, checked_in, date. Output: turnout rate and improvement actions.
60. Seasonal pricing guardrails: You are a pricing engineer. Task: define guardrails for seasonal price changes. Context: season, ADR, occupancy. Output: guardrails table and triggers.
61. Competitor feature map: You are a competitive analyst. Task: map competitor features to pricing. Context: features, rates, occupancy. Output: feature map with implications.
62. Guest readiness checklist: You are an operations analyst. Task: create a guest readiness checklist to improve reviews. Context: amenities, communication, timing. Output: checklist with Excel-ready status columns.
63. Localization impact: You are a market analyst. Task: analyze impact of localization on bookings. Context: language, currency, reviews, bookings. Output: localization score and two optimization tactics.
64. Data reconciliation plan: You are a data engineer. Task: reconcile data from multiple sources for Airbnb metrics. Context: sources, mappings, integrity checks. Output: reconciliation plan and example formulas.
65. Market demand signals: You are a market analyst. Task: identify leading demand signals for Airbnb in the target market. Context: data: inquiries, saves, searches, bookings. Output: signals list with recommended actions.
66. Inventory aging report: You are a portfolio manager. Task: age of inventory by listing. Context: listing_id, days_online, days_booked. Output: aging report and disposal/retention tips.
67. Pricing ladder: You are a pricing strategist. Task: build a pricing ladder for tiers of listings. Context: tier, ADR, occupancy. Output: ladder table and tier-specific prompts.
68. Occupancy loyalty analysis: You are a loyalty analyst. Task: analyze repeat guests and loyalty effects on occupancy. Context: guest_id, bookings, occupancy. Output: loyalty score and retention plan.
69. Data privacy checklist: You are a compliance analyst. Task: ensure Excel analytics comply with privacy rules. Context: data_fields, access, retention. Output: privacy checklist and access controls.
70. Master KPI list: You are a KPI engineer. Task: define a master set of Airbnb analytics KPIs. Context: metrics, targets. Output: KPI table with definitions and calculation methods.
71. Noise complaint risk: You are a risk analyst. Task: assess impact of noise complaints on occupancy and rating. Context: complaints, rating, occupancy. Output: risk score and mitigation plan.
72. Refund timing optimization: You are a operations analyst. Task: optimize refund timing to balance satisfaction and cost. Context: refund_amount, days_to_resolve, rating. Output: policy suggestion and expected impact.
73. Weekly pacing dashboard: You are a dashboard designer. Task: design a weekly pacing dashboard for occupancy and revenue. Context: weekly data, targets. Output: layout plan and sample formulas.
74. Guest review prompts: You are a UX writer. Task: craft review prompts to elicit constructive feedback. Context: listing, past guest rating. Output: 6 templates and guidance for personalization.
75. Industry trend comparison: You are a market analyst. Task: compare local market trends to your portfolio. Context: ADR, occupancy, revenue by quarter. Output: comparative table and 2 strategic moves.
76. Data pipeline map: You are a data engineer. Task: map data pipeline for Airbnb analytics. Context: sources, ETL steps, data model. Output: pipeline diagram description and success criteria.
77. Pricing experiment plan: You are a researcher. Task: design an A/B price experiment in Excel terms. Context: control_rate, test_rate, duration. Output: experiment plan, success metrics, and sample size guidance.
78. Guest lead time report: You are a data analyst. Task: report on lead time distribution for bookings. Context: lead_time_days, bookings. Output: distribution chart plan and recommendations.
79. Occupancy risk heatmap: You are a risk analyst. Task: create a risk heatmap for occupancy by listing and month. Context: occupancy_rate, listing_id, month. Output: heatmap plan and interpretation notes.
80. Fueling occupancy growth: You are a growth analyst. Task: propose data-driven tactics to grow occupancy. Context: occupancy, ADR, reviews. Output: 5 tactics with expected impact and Excel-ready measurement.
81. Pricing by weekend: You are a pricing specialist. Task: create weekend-specific pricing plan. Context: day_of_week, occupancy, ADR. Output: weekend-rate rules and validation checks.
82. Cancellation sensitivity: You are a sensitivity analyst. Task: show revenue sensitivity to cancellations. Context: cancellations, revenue, bookings. Output: sensitivity table and recommended levers.
83. Guest satisfaction drivers: You are a data analyst. Task: identify top satisfaction drivers from data. Context: rating, response_time, inquiries_resolved. Output: driver list with recommended improvements.
84. Room type mix: You are a portfolio analyst. Task: analyze revenue by room type. Context: room_type, revenue, nights_booked. Output: mix report and 2 optimization ideas.
85. Competitor rate drift: You are a pricing analyst. Task: measure rate drift vs competitors. Context: listing_id, rate, competitor_rate. Output: drift report and recommended reactions.
86. Booking pattern anomaly: You are a data anomaly detector. Task: detect unusual booking patterns. Context: bookings, holidays, listing_id. Output: anomaly flags and suggested checks.
87. Seasonal demand plan: You are a demand planner. Task: create a seasonal demand plan for the year. Context: month, occupancy, ADR. Output: plan with targets and risk notes.
88. Occupancy vs occupancy age: You are a data analyst. Task: compare occupancy for new listings vs established. Context: listing_age, occupancy_rate. Output: comparative chart plan and actions.
89. Cost center analysis: You are a financial analyst. Task: assign costs to listing-level cost centers. Context: costs, revenue, listing_id. Output: cost per listing and profitability map.
90. Guest support SLA: You are a operations manager. Task: set service level agreements for guest support. Context: response_time, resolution_time, tickets. Output: SLA table and escalation plan.
91. Marketing attribution: You are a marketing analyst. Task: attribute bookings to marketing efforts. Context: channels, bookings, revenue. Output: attribution model and 2 optimization ideas.
92. Data security plan: You are a compliance analyst. Task: craft a data security plan for analytics. Context: data_access, encryption, retention. Output: plan with controls and sample policy.
93. Listing-level insights: You are a portfolio analyst. Task: generate insights per listing. Context: listing_id, metrics. Output: 1-page insight sheet per listing with action items.
94. Forecast vs realized: You are a forecasting analyst. Task: compare forecast to realized occupancy and revenue. Context: forecast, actuals, horizon. Output: variance report and explanation.
95. Guest intent classification: You are a data scientist. Task: classify guest inquiries by intent in Excel-ready format. Context: inquiries, categories. Output: labeled dataset and sample prompts.
96. Cleaning schedule optimization: You are an operations analyst. Task: optimize cleaning schedules to minimize downtime. Context: turnover_time, bookings, staff. Output: optimized schedule plan and impact estimate.
97. Pricing guardrail audit: You are a pricing auditor. Task: audit guardrails for pricing rules. Context: rules, ADR, occupancy. Output: audit findings and remediation steps.
98. Market entry readiness: You are a market analyst. Task: assess readiness for market expansion. Context: demand, competition, listings. Output: readiness score and recommended steps.
99. Yearly KPI forecast: You are a KPI forecaster. Task: forecast yearly targets for key metrics. Context: current_year_data, seasonality. Output: target table and monitoring plan.
100. Excel automation checklist: You are a data automation specialist. Task: create an Excel automation checklist for Airbnb analytics. Context: data, macros, templates. Output: checklist with risk notes and sample macros.

Best Practices

• Keep prompts specific to avoid ambiguous results.
• Use listing_id level prompts to drill into performance, then consolidate for portfolio-wide insights.
• Flatten complex outputs into structured tables that can be pasted into Excel without reformatting.
• Color-code outputs or provide Excel-ready formatting notes to speed up dashboard assembly.
• Test prompts with a small data sample before running on the full dataset to catch misinterpretations.

Common Mistakes to Avoid

• Asking for outputs without defining the data fields or date ranges, leading to incomplete results.
• Using vague prompts like analyze revenue without specifying currency, seasonality, or aggregation level.
• Overloading prompts with too many objectives, causing scattered and hard-to-parse results.
• Failing to specify the output format, so results require manual reformatting in Excel.
• Neglecting validation steps, resulting in outputs that look plausible but are inaccurate.

FAQ

What kind of data do I need to use these prompts effectively?

You should have clean, tabular data with fields like listing_id, date, ADR, occupancy, nights_booked, revenue, platform_fees, and expenses. The data should be organized by listing and time period.

Can I adapt prompts for a single listing or a portfolio?

Yes. You can run prompts at the single-listing level for detailed insights or aggregate results for portfolio-wide analysis by tweaking scope placeholders.

Are these prompts compatible with other spreadsheet tools?

The prompts are designed to produce outputs that Excel and compatible spreadsheets can readily import, such as CSV-ready tables and pivot-friendly formats.

How do I convert prompts into dashboards?

Use the output tables as data sources and apply Excel features like pivot tables, charts, and slicers to build interactive dashboards.

What about data privacy and security?

Ensure access is restricted to authorized users, anonymize sensitive fields when sharing, and follow your local data privacy regulations.

How do I validate the results from these prompts?

Cross-check totals against known benchmarks, run spot checks on sample rows, and compare results with standalone calculations to confirm accuracy.