Guest Segmentation Model: This model segments the population of guests using cluster analysis and decision trees. Segmentation is one of the first and most basic machine learning methods. Segmenting the population of guests into distinct segments is important because creating separate model for separate segments may be time consuming and not worth the effort. But, creating separate model for separate segments usually provides higher predictive power.
Overall Property Preference Model: This model uses logistic regression to identify whether a customer is attracted by Restaurants, Bars or Shops (or combination).
Customer Day Preference Model: This model looks at guest behavior by day and identifies the day preference for attending. This model can be extended to time of day preference. This model helps hotel managers with staffing and layout requirements when mixed with other analysis.
F&B Location Preference Model: This model looks at carded spend across food venues to identify guest’s preference for eating. This model is useful for menu changes, and for the creation of marketing offers around F&B. For instance, it could show the steakhouse could benefit from opening earlier in the week lining up with when the big spenders are hoping to attend.
Hotel RFM Model: This model forecasts VIP guests using revenue for F&B and Entertainment as well as frequency of visits and days since last visit.
Comments are closed, but <a href="https://www.qlx.com/catalog-of-predictive-models/trackback/" title="Trackback URL for this post">trackbacks</a> and pingbacks are open.