What is PMI prediction? 

PMI uses a combination of Machine Learning (ML) and statistical models to automate forecasting of revenue and units (covers, room nights, guest nights etc.). It uses historical data to identify trends (seasons) and adapts to specific properties over time based on their activity. 

How is PMI prediction calculated? 

You can view the PMI prediction values in the Live forecast module. To learn more about a specific date’s prediction, click on the PMI prediction cell. 

1. In the top section you see the prediction details 
   1. Lead time: How far out is this day. E.g. tomorrows forecast has lead time 1. 
   2. Seasons: The date comparison set used to forecast. See ‘Seasons’ section below. 
   3. The text in brackets (S1, LeadT, DoW) are the forecasting models being used. See ‘Forecasting models’ See section below. 
2. The first table shows relevant historical dates.
3. The final section is ‘discarded dates’ – dates that were in the correct season on the same week day but were disregarded in the forecasting algorithm as outliers. Hover over the red question mark to see the reason. See ‘Outliers’ section below. 

Forecasting models 

There are four different forecasting models (1 statistical, 3 Machine Learning), and each model generates a new forecast every day for the next 16 months. The one with the best accuracy is used in PMI Prediction. 

1. Statistical model 
   1. S1: Uses historic data from the season and weekday to forecast the future. It reacts instantly on any change that is done affecting the target date. As it is only using historical data, it can take time to react to new trends or situations. 

2. Machine learning: The main benefit for ML models is that they learn each property separately and will adapt the features according to the specific property. Over time it will therefore improve the forecasting accuracy. 
   1. LeadT (Lead time): Has one sub-model for each lead time. This means the features used and the importance of each differs depending on what lead time is being forecasted. Note – weekday is used as a feature, so the day of the week still plays a role in this forecast.  
   2. DOW (Day of the Week): Has one sub-model per weekday. Uses the day of the week to determine the importance of the features that create the forecast. Note – lead time is used as a feature so still plays a role in the forecast. 
   3. Comb (Combination): Uses an average from the 2 above forecasts. 

Seasons 

What is a season? 

Seasons are groups of historic dates with similar behaviours in revenue and activity in the hotel. PMI Prediction uses seasons to identify dates that can be used to forecast the future. The more similar the dates are, the more likely it is that they “behave” in a comparable manner. 

Seasons are generated automatically based on the data in PMI. These cannot be edited. 

To view the seasons, go to Live forecast Tools > PMI Live forecast > Tools > Seasons. 

The items with a grey frame around the date in the calendar are the Rolling Trend Season (RTS). These are dates that create a bridge between seasons to give the algorithm more dates to work with, and make more recent history more important than previous years. 

What is an outlier? 

An outlier is something that is abnormal for the specific weekday and season. For example, If a property usually closes during Christmas, it is normal that these dates have 0 revenue. If one day then has sales, that day will become an outlier as 0 is considered as normal. 

A date set as an outlier will be disregarded when it comes to forecasting.  

Most outliers are detected automatically.  

Subject to user rights, you can also add manual outliers. To do this, go to Live forecast >Tools > PMI Live forecast > Tools > Seasons, and add a new label with an appropriate name. In the dropdown select ‘Outliers’.

Outliers should only be used when there are significant changes in prices, offerings, or unusual events that are unlikely to happen again. Manual outliers should rarely be used for just a day or two, but instead when it is occurring on multiple days. 

Remember that the auto detection of outliers will cover most of the dates that should be outliers, so the manual outliers is only a complement when the exception has occurred on so many days that the standard auto detection have considered them to be normal.