PMI Knowledge base

Generic filters
Exact matches only
Search in title
Search in content
Search in excerpt
Filter by Custom Post Type
PMI Knowledge Base
Article contents (TOC)
Print

SMART Forecast enhancement – September 2022

Please Share Your Feedback
How Can We Improve This Article?

What is SMART v2.0?

SMART v2.0 is an enhanced version of the existing SMART forecast which is a prediction of how many labor hours should be scheduled according to expected activity in the hotel.

This replaces the existing SMART forecast, shown as the yellow line on the graph in the cockpits. The label remains the same (SMART forecast)

What is SMART v2.0’s purpose?

The purpose of the update is to provide a more realistic suggestion for daily allocation of hours in line with the department’s needs.

It shows a recommended use of the hours determined in the monthly forecast by either the forecast hours or forecast productivity (depending on tool setting).

The SMART v2.0 uses Machine Learning (ML) to recognise trends from previous periods and allocate the hours appropriately.  Due to COVID-19, historic data from March 2020 up to (and including) February, 2022 are disregarded when analyzing historic data to predict future trends.

How is it calculated?

SMART v2.0 follows the same basic principle as SMART forecast to predict the number of productive hours needed for a month.

If ‘Locked target’ in Tools is set to ‘Productivity’ (this is the default option), it takes the expected activity of the hotel (Cost driver) divided by the productivity forecast to calculate the number of hours. For example, a hotel expects to have 100 room nights (cost driver) this month, and the Housekeeping target is to clean 2 rooms per labor hour (productivity forecast). So SMART forecast would calculate Housekeeping hours needed for the month as 100/2 = 50 hours.

If ‘Locked target’ is set to ‘Hours’ it allocates the forecasted monthly hours based on the daily activity at the hotel.

To change the Locked target, you need to have Administrator user rights in PMI.

SMART v2.0 then uses Machine Learning to allocate the hours per day. It looks at the expected activity each day, as well as trends from previous periods to recommend daily staffing.

For example, if there are many check-outs on a Sunday, but housekeeping usually waits until Monday to clean all rooms, the SMART Forecast v2.0 will recognize this and suggest more hours on the Monday, even if activity levels are higher on the Sunday.

This is different from the previous SMART, which only considers the same day activity. SMART v2.0 can also use more information than the primary cost driver to decide how to allocate hours. Several other factors can be used for a single day. For example, arrivals/departures, activity on other days/departments etc.

The same logic applies to SMART Budget.