For Hotel Revenue Managers ·
What you'll accomplish
You'll build a repeatable monthly workflow to identify demand-driving events in your market — concerts, conventions, sporting events, citywide conferences, graduations, and other generators that affect hotel demand. Using ChatGPT Plus with web browsing, you'll research a 90-day rolling horizon each month, produce a structured event calendar with demand impact ratings, and generate the forward-looking section of your GM and ownership reports from that same data.
What you'll need
ChatGPT Plus includes web browsing via the default GPT-4o model. To confirm it's active:
Web browsing lets ChatGPT research actual upcoming events rather than relying solely on its training data — critical for identifying events 60-90 days out.
Create a short reference document you'll paste into each research session. This ensures ChatGPT searches the right venues for your specific market.
Example:
[City] key demand-generating venues:
- Convention center: [Name], [capacity], [address or URL]
- Arena: [Name], [capacity] — concerts, sports, special events
- Stadium: [Name], [capacity] — [teams/events]
- University: [Name] — graduation [month], football [season], conference events
- Fairgrounds/festival venue: [Name]
- Hotel-based convention space: [Name] — major group events
- Other: [major employer campuses, hospitals with annual conferences, etc.]
CVB calendar: [URL]
Ticketmaster/StubHub search terms: "[City] events", "[arena name] events"
On the first Monday of each month, run this research sequence:
Prompt 1 — Upcoming events sweep:
I'm a hotel revenue manager in [city]. I need to identify all upcoming events in my market for the next 90 days ([date range]) that would drive hotel demand.
Please search for events at these venues: [paste your venue list].
Also check: [CVB URL if you have it], Ticketmaster for [city], and any major convention or conference calendars for [city].
Format your results as a table with these columns:
- Date(s)
- Event name
- Venue
- Expected attendance (estimate if not available)
- Demand impact: High / Medium / Low / Unknown
- Notes (any booking pattern implications — multi-night, room blocks, advance purchase)
Prompt 2 — Demand stacking analysis:
Based on the event list above, identify any "demand stacking" situations — weekends or periods where multiple events overlap. Which dates have the highest combined demand potential? Rank the top 5 highest-demand dates in the next 90 days and explain why.
Prompt 3 — Rate strategy implications:
For the top 5 high-demand dates you identified, what rate strategy would you recommend for [Hotel Name] ([room count] rooms, [segment], typically priced at [X] vs. comp set)? For each date: recommended rate position (premium, parity, or below-parity), suggested advance purchase or restriction strategy, and lead time for rate action.
After running the research, copy the output into your demand tracking tool:
In Excel/Google Sheets: Create a tab called "Demand Calendar" with columns: Date | Event | Attendance | Demand Impact | Rate Trigger | Action Taken | Notes
In your RMS: Add event notes to high-demand dates in your RMS calendar or manual pricing notes — this connects the event context to your rate decisions.
In your GM report: The forward-looking section of your weekly GM report should reference the top 1-2 upcoming demand events — this positions you as proactive rather than reactive to ownership.
Add a recurring calendar event: "First Monday — 90-day demand research (ChatGPT)"
This becomes a 20-minute monthly task instead of an ad hoc search whenever you're concerned about a specific period.
Specific event impact analysis:
[Event name] is happening in [city] on [dates] with approximately [X] attendees. This is a [event type — convention, concert, sporting event]. How would this event typically affect hotel demand? What is the typical booking window (how far in advance do attendees book)? What restrictions (MLOS, CTA, advance purchase) are commonly applied for this type of event?
Event comparison — year-over-year:
[Event name] happened last year on [dates]. Based on my data, we ran [X]% occupancy at $[X] ADR that weekend. This year, the same event is on [dates]. Based on current rate shopping, our comp set is pricing at $[X-Y] range. Should we price higher, at parity, or lower than last year? What factors would change our strategy?
Last-minute soft period analysis:
We're [X] days from [date] and running [X]% occupancy vs. a forecast of [X]%. Are there any late-breaking events or demand generators in [city] around that date I should be aware of? Also, what are typical last-minute demand recovery strategies for a [segment] hotel in a soft period this close to arrival?
CVB and conference calendar research:
Search for citywide conferences and conventions scheduled in [city] for [year], particularly any that would require 500+ hotel room nights. I'm looking for: event name, dates, venue, estimated attendance, and whether they are annual (likely to repeat) or one-time. Format as a table.
New event impact assessment:
A new [annual event type — e.g., tech conference] is coming to [city] for the first time on [dates] with an expected [X] attendees. We have no historical data on this event. How should I approach pricing for this unknown event? What signals should I watch in the 90 days leading up to it to calibrate my rate strategy?