Revenue driver explained
What is a revenue driver?
A revenue driver is what drives the revenue of a department. For example, if more guests are staying at a hotel, the restaurant can expect to generate more revenue. There is often more than one driver that impacts revenue in a department.
A driver-based forecast uses these drivers to forecast for the department. For example, a restaurant may use Guest nights as a driver to forecast the number of covers.
How to review and update the driver
If set-up has selected to use PMI machine learning algorithms, the driver detection will be automated based on seasons and day of the week. It will create different drivers per segment and, if units/covers are used, separate drivers for these. This is recommended for properties with at least 1 year of historic data in PMI. It is possible to use ML (Machine Learning) drivers with only 5 weeks of history, but the accuracy will increase as the amount of historic data available increases.
To view the drivers being used:
- Go to tools. Select ’Driver based’
- Use the graph to review the results and evaluate the usefulness of the drivers. You cannot make any edits to drivers when ML drivers are activated. Consider if your department could achieve a more accurate forecast with a manual driver.
- ML drivers are detecting correlations between the department’s historical covers/units/revenue and other departments/segments (sources). There can be more than one source per day of the week which can make it difficult for humans to understand the correlations. We therefore recommend using the graph for a general evaluation of the accuracy of the drivers, instead of checking the sources in the table.
Manual drivers are usually used for new properties with less than 1 year of historical data available, or for properties that have recently been through significant changes that make historic patterns an unreliable source for future.
To create a manual driver:
- Go to Tools and select Driver based
- Use the drop-down menus to define which segment (if enabled) you want to build a driver for.
- Choose the source. You can also define which segments within the source you want to build the driver from.
- Choose if you want the calculations by weekdays or just as a total (unticked radio box).
- After you have defined settings, click on the + sign and the rule for this segment is moved up in the rate grid list. You may build several drivers for one segment or department.
- After all the rules have been created, choose if you want the entire forecast to be based on the rule. 100% means everything, but if you want to revise e.g., 30% of the revenue manually, change the cell with percentage to 70. If you have a positive change in the revenue with 10% on specific days or in total, you can change the percentage to 110%.
- Applicable for covers only: Define capture ratio for both cover/units and rates. You may untick both these buttons if desired.
- Applicable for covers only: An easy way of letting the system help you is by clicking on one of the two blue buttons, From Budget or From History. From Budget means that PMI splits the budgeted data per day based on last year’s actual figures. It will suggest the same average check, but different number of covers each day. In other words, PMI calculates the budgeted capture ratio of occupancy; e.g., if your budget is 100 covers and guest nights are budgeted at 1000, the capture ratio would be 10%. This is usually recommended to new hotels that don’t have any historical data.
- Applicable for covers only: From History means that PMI calculates each departmental segment individually, giving you different averages for each segment, and different average rates, based on last year’s actual figures. For example, if you had 10 guests on average, last year on Mondays, and the guest night occupancy was, on average, 100, PMI will calculate 10% of guest nights as the capture ratio for this period.
- You may calculate for just some of the rules as well. Use the radio button next to the rule to activate or deactivate for calculation.
- You may manually revise the ratios directly in the cells at any time. You can also make a New Period for different seasons that influence the average revenue. For example, summer is a slow season with guests spending less money, on average, in the restaurant, than in the autumn with conference guests on average spending more.
- Make sure that you save the changes.
Troubleshooting tips
This section provides additional troubleshooting advice for readers experiencing specific issues. While it’s packed with useful insights, you may skip it if you’re not facing any related problems.
Why is the hours total different in the table and the graph?
The difference in hours comes down to the type of forecast being displayed:
- Management Forecast (Table): This is the forecast set manually by management, based on their expectations and strategic goals. It reflects planned hours to meet operational needs.
- SMART Forecast (Yellow Bar in Graph): Generated by PMI’s SMART system, this forecast uses machine learning and historical data to provide a dynamic suggestion. It factors in monthly productivity goals and current hotel activity.
The variation between these two forecasts highlights the difference between static planning (Management Forecast) and data-driven predictions (SMART Forecast). Use this insight to adjust plans as needed for better alignment with real-time performance and goals.
Why can’t I edit the forecast for a closed or previous period?
In PMI, forecast periods like May can become locked after a certain point to protect finalized data. If you have the right role (e.g. Operational Manager, Controller), but still can’t edit, it’s likely due to Period locking being active.
What to do:
Check Period Locking:
- Go to Advanced settings > Period locking
- Look for a padlock icon next to May.
- If it’s locked, click to unlock — this will open the period for editing.
Still can’t unlock it?
- You may have edit rights, but not access to Advanced Settings.
- In that case, ask your administrator or HQ finance contact to unlock it for you.
Once unlocked, you can go back to your module (Cockpit, Forecast, etc.) and make the changes you need.
Understanding zero OTB in Flash report
In PMI, the Flash Report provides a daily overview of revenue figures, both actual and forecasted, across all departments. Users may encounter situations where the Flash Report displays zero On the Books (OTB) data for specific dates leading to concerns about data accuracy.
Clarifying OTB in Flash Reports
It’s important to note that the Flash Report does not directly display OTB figures. Instead, it presents actual revenue data up to the current date and relies on the Live Forecast for future dates. The Live Forecast incorporates OTB data, which represents revenue from existing bookings or sales for upcoming dates. Therefore, if revenue actuals are zero for specific dates, the OTB for those dates will also be zero, reflecting no current bookings or sales recorded.
Manual changes overwritten at Live forecast import
Legacy PMI System
- Issue: Pickup column doesn’t “gray out” when importing Live forecasts.
- Cause: This is the design of the legacy PMI system.
- Effect: Manual changes in the pickup column will be overwritten with each import.
New PMI System
- Preserving Manual Changes:
- Enable Editing: Click the robot icon (if auto-forecasting is enabled) or the import icon next to the day you want to edit.
- Edit Value: Enter your desired value in the pickup column (only editable column for future days).
- Save Changes: Press “Save”.
- Result: Your changes will be preserved even after a new import, indicated by a person with a pencil icon.
Live forecast warning for One-Off events
Issue: Some dates in the Live forecast may show a red warning triangle, indicating that PMI prediction could not generate an automated forecast for that date.
This usually happens when:
• There is insufficient historical data
• Many historical dates for that day have been marked as outliers or excluded
What to Look For:
- A red warning triangle appears next to the date in the Live Forecast
- This icon signals that the system could not generate a forecast
- Hovering always display a text
What to Do:
- Click the triangle or review the flagged date
- Consider whether the activity is linked to a one-off event (e.g., concerts, closures), but keep in mind that if there isn’t enough historical data, this limitation cannot be influenced by the user.
- If PMI cannot generate a forecast for a specific date, enter a manual value to maintain reporting accuracy — but note that manual forecasts do not influence future automated predictions. Only manually added outliers in the season calendar can affect future forecasts.
Related: To learn how PMI Prediction filters out unusual events so they don’t distort future forecasts, see What is an Outlier?”
How to handle temporary room closures (due to renovation) in PMI
If some rooms are temporarily closed due to renovation, you can adjust your forecasts in PMI to ensure productivity and cost-driver metrics remain accurate.
1. Adjust Cost Drivers in the Forecast: To reflect reduced room availability:
- Go to the Revenue forecast view (under Live Forecast)
- Select the affected period (e.g. renovation month)
- In the Room nights or Available rooms field, enter the reduced number of rooms for the affected dates
- Save your changes
These changes will immediately update your Live forecast and influence related cost drivers in labor cockpits.
2. Resubmit the Forecast
After adjusting room counts:
- Click Submit in the Forecast view
- This ensures that the adjusted forecast becomes the basis for calculations in Cockpits and P&L
3. Check SMART Hours
If SMART scheduling is used:
- Navigate to the Labor cockpit
- Verify that SMART hours have adapted to the new room volumes
- Use Sense check or the visual graph to confirm no unrealistic spikes or dips remain
How to confirm that forecast targets are correctly applied
To ensure forecast targets are properly set and reflected in PMI — whether for a coaching session, planning review, or operational check — follow these quick steps:
Check the Budget & Forecast Module
- Go to Budget & Forecast
- Select the relevant month
- Confirm that productivity targets and hours are entered for all departments
Review the Labor Cockpit
- Navigate to the Labor Cockpit for the same period
- Ensure that SMART hours match your targets
- Look for any red hygiene warnings that indicate missing or outdated inputs
Verify Lock Settings
- In the Cockpit, check whether productivity or hours are locked
- Locked values ensure targets won’t shift if cost drivers change
Confirm with Department Heads (if needed)
- HODs should verify that targets align with real operational needs
Tip: If anything’s missing or needs adjusting, update and save the forecast to apply the changes system-wide.
How to check if forecasts have been submitted for the next 3 months
If you want to confirm whether all hotels have submitted their forecasts for the next three months, the steps depend on your access level.
If you have access to the Planning module:
- Open the Live Forecast module
- Use the Submit Several or Approve Several options under the Tools menu
- The table will show:
- Each property
- Latest forecast submission date
- Status (e.g. Pending, Ready, or Locked)
If you don’t have Planning access:
You can still check forecast status in the P&L Status tool:
- Go to Tools → Status
- Select the property and month range
- Look at the Room Revenue department (typically Reception or FO)
- If the status is Ready or Locked, the forecast has been submitted
For General Managers:
If you only need to check Room Forecast:
(Note: This feature is only available in the current version, not the legacy one)
- Open Rooms Live Forecast
- Switch to Table View
- Scroll through the upcoming three months
- Use Sense Check to spot any missing or unusual data
- Submission status via Go to P&L → Tools → Status to confirm whether the Room Revenue forecast is submitted (Ready/Locked) or still Pending.:
Note: Forecasts are considered submitted when their status changes from Pending to Ready or Locked.<
How to change covers on historical dates
If you need to update covers on a past date, use the Flash Report instead of Live Forecast. Follow these steps:
- Navigate to the Flash Report.
- Select the historical date you wish to edit.
- Click on the Edit tool (Pen icon).
- Manually adjust the covers as needed.
- Save your changes.
Note:
- Live Forecast is designed for adjusting future covers.
- Flash Reports handle updates for historical data, such as revenue and actual figures.
Flagging one-off events
Scenario: A single day (concert, trade-fair, planned outage, etc.) will spike or dip demand. If you leave it untouched, PMI Prediction will use normal history and likely forecast too low (or too high). After the day passes PMI will auto-classify it as an outlier, but you still need an accurate forecast today for staffing and revenue planning.
Step 1 – Override the day in Live Forecast
- Go to Rooms ▸ Live Forecast.
- Select the unusual date.
- Switch the cell to manual and enter the room-nights and ARR you expect.
Step 2 – Save / Send to Forecast
Click Save / Send to Forecast (green button).
This locks your manual value and pushes it to Cockpits and labour tools so staffing and cost-drivers follow the adjusted forecast.
What happens next?
- During the day: all reports, RevPOLU, and staffing hours use your manual forecast.
- After the day closes: PMI will automatically decide whether that date should be flagged as an outlier. If it is, the spike won’t distort future ML forecasts—no extra action needed.
Remember: manually overriding the Live Forecast fixes today’s planning; it does not teach the model a new pattern. Only the outlier engine—run after actuals arrive—decides whether to exclude the date from future history.
Excluding segments from driver-based calculations
It is not possible to stop Machine Learning (ML) from including an existing segment in the driver-based calculation. If the ML Live Forecast doesn't align with your expectations, you have the option to manually override it or construct a custom driver to make necessary adjustments.
Enhancing forecast accuracy: Leveraging PMI’s auto forecasts
Discrepancies in the imported Room Night live forecast can impact the generation of live forecasts for arrivals, departures, and stayovers. To address this, it's recommended to utilize PMI's auto forecasts. These forecasts are typically more accurate as they rely on machine learning and historical data. Ensuring the accuracy of the imported Room Night live forecast is crucial, as it directly influences the precision of your live forecasts. Regularly review and adjust your forecasts to maintain their reliability and effectiveness.
Different hours for similar revenue on different dates can vary!
Recommended hours for similar revenue on different dates can vary due to a combination of factors including the monthly productivity forecast, historical staffing patterns, and other factors recognized by the machine learning capabilities of the SMART forecast.
Difference Between Live Forecast and PMI Prediction
If there is a recalculation of the PMI Prediction due to season generation, new file import, or manual calculation, it takes time for the ML algorithms to fully update. The Live forecast values will only update once all dates in the viewed period are completely updated. Thus, there might be a delay, and the Live forecast might not immediately match the PMI Prediction.
Changing revenue for today & tomorrow in PMI
Key Points to Remember:
- Budget & Forecast Module changes totals on a monthly basis only.
- Flash Report allows you to edit historical values.
- Live Forecast allows you to edit future values (including today and tomorrow) by switching to “manual.”
Steps to edit revenue for historical dates (Past)
- Open the Flash Report.
- Expand or select the past date you want to edit; click the plus icon.
- Click the pencil icon (if available) to override the revenue value.
Steps to edit revenue for future dates (Today & Tomorrow)
- Go to the Live Forecast.
- Expand or select the specific date (e.g., today, tomorrow).
- Switch the date to “manual” if required.
- Enter the new revenue value in the editable field.
Can you activate a Live forecast accuracy report in Power BI?
The PMI system integrates Live forecast accuracy into its PMI Index calculations. Although Live forecast accuracy contributes to the PMI Index, it is not explicitly shown as a separate report in PowerBI.
Best practice cadence for keeping live forecasts current (for Staff planning)
To ensure your Live Forecast reflects upcoming trade-fair periods — especially for effective staffing — follow this practical cadence:
Monthly Cadence:
Update the Live Forecast early
- Make adjustments to the Live forecast in the Revenue forecast view
- Do this as soon as trade-fair dates or demand changes become clear, ideally before the 20th of the current month
Review key dates for next month
- Scroll to next month in the Revenue Forecast view
- Check if key trade-fair dates are already reflected (volume, rates, etc.)
- If not, manually adjust the forecast for those dates
Monitor how changes affect labor
- Once the Live Forecast is saved, the updated figures feed directly into the Labor cockpits, which use these forecasts to calculate SMART hours
Repeat monthly
- Revisit the forecast by mid-month for the following month
- This rolling review ensures staffing is aligned well in advance
Note: There is no need to “submit the forecast to Cockpits” — once saved, the Live Forecast automatically updates the relevant dashboards and labor planning tools.