One of the arguments I continually make in this blog is that many Total Revenue Management efforts are being thwarted by the fact that managers are using the wrong measures to construct TRM strategy. In brief, you can not use traditional hotel measures of performance and analysis to drive a TRM transformation.
To achieve true Total Revenue Management, you need to follow and value your guests footsteps throughout their stay. Luckily, we can use a few very powerful Data Science algorithms to map out the seemingly random decision processes that your guests use.
Here are three cases studies, based on real consulting engagements, where measures based on more advanced analytics where used to highlight hidden guest behavioral patterns that were destroying profit.
GM: Dinner Impossible
The Challenge:
The GM needs to promote restaurant visits. Restaurant sales have been stagnating. As a first line of attack, the GM changed the menu a few times but there has been no improvement in Sales. As a second line of attack, the GM tried to incentivize the front desk and concierge to increase in-restaurant visits – again, to no avail. The GM is particularly interested in understanding the guests’ footsteps throughout their stay to find out if there is any pattern of behavior that can be exploited to increase restaurant visits.
Hotel Data Science Technique: Bayes algorithm
The Key Influencers report allows the GM to see which guest activity most influences a given target (in this case – In Restaurant service) using Bayes’ theorem. The algorithm finds the strongest associations in guest behavior across all touchpoints. The report the we produce then tells you exactly where your efforts ought be focused in order to have the best chance of achieving your best results. The report is ideal for studying issues that are beyond any individual department or outlet which is the definition of Total Revenue Management.
