For years, hoteliers have been challenged by unpredictable economic forces, inexplicable trends and at-times chaotic world events. Amongst it all, revenue managers have been on the front line, trying to minimise losses and improve forecast accuracy.
Despite great advances in automated decision-making systems during the past two decades, a lack of trust in technology has held the industry back from garnering deeper insights from forecasting. The past few years have forced us to do more with less and shown the need for sophisticated systems that use comprehensive data sets intelligently.
Best-in-class revenue management systems measure uncertainty by creating an unconstrained demand forecast, which in turn produces a more accurate overall forecast. The hotel technology landscape is diverse, particularly the range of tools which target forecasting and revenue management. Understanding the differences between systems is essential to avoid pitfalls: how do rules-based systems compare to automated? How can you avoid your decision-making falling into a silo by choosing the wrong type of optimisation?
Understanding rules-based versus AI-driven systems
Put simply, rule-based systems use pre-defined ‘If/Then’ statements to set triggers which dictate actions within the system. For example, if occupancy reaches 20 per cent, then the room rate will increase by 10 per cent.
These systems will only execute predefined actions – and will continue doing so until you tell it to stop. Every eventuality needs a written rule to ensure action is taken; if there is no rule in place, the system won’t take any action. If an error is made when inputting a rule, the system will still blindly follow that rule which can harm your business.
Rule-based systems are commonly confused with artificial intelligence and machine learning systems; however, they are neither – although they seemingly work on their own, they do exactly as instructed by a human. While AI-driven systems learn and adapt to determine the best action based on data behaviours without needing predefined parameters.
The downsides to rule-based systems
Rule-based systems rely on revenue managers having the time to constantly check, revise and create rules. This process can be just as complex as installing an algorithmic approach due to the number of variables within the hotel booking process including the type of guest, their booking and stay needs.
At times, rules can come into conflict with one another – for example, you may have a rule set to provide value-adds for people staying 5 or more nights at a resort hotel, and a separate rule stating no value-adds for people booking an entry-level room type. If not set up within a complex hierarchy correctly, rules can reflect rates that confuse your guests, forcing them to go elsewhere to book.
Group pricing is a particular hurdle for rule-based systems, especially when enquiries include food and beverage spend. The variable needs of group bookings simply aren’t conducive to rule-based systems, creating manual work for in-house reservations teams and often causing delays in responding to group business enquiries as the sales, reservations and revenue teams debate which piece of business to take.
In businesses where there is sufficient human expertise to define (and constantly redefine) the rules, rule-based systems may work for simple problems. But results are variable – depending on the quality of the revenue manager, their knowledge of the marketplace, diligence in creating rules, and time invested on a regular basis in creating and adjusting rules.
Rule-based systems tend to fall short of their purpose when revenue managers are absent, on holiday, indisposed to other priorities, or leave the business (with a new team member usually needing to start from scratch and overhaul the system to ensure they know the intricacies of existing rules).
An accurate forecast in tricky circumstances can only be created by an intelligent automated system, one that continually learns and can process thousands of data points faster than a human can. Such systems allow hotels to respond dynamically to changing market conditions 24 hours, 7 days a week – even handling individual booking nuances.
Boosting pricing power while dealing with uncertainty
Revenue management and price optimisation decisions encompass too many variables for the human mind to effectively analyse in real time. To provide a more accurate decision-making capability, systems need to model real-life situations and react intelligently in the blink of an eye to stay on top of market trends and work within the context of a hotel’s business objectives.
While stagnant, unadjusted rules leave money on the table, an automated system helps hoteliers deal with uncertainty and be proactive in rate management, boosting their pricing power.
From a data perspective, a hotel’s stay structure is a complex time-based network built around multiple interacting arrival days, length of stay, and room category combinations. It must consider qualified and unqualified guest types, each with its own distinct demand. Mix in the uncertainty with respect to booking patterns, seasonality, no-show rates, etc, and you have complexity beyond human analysis capabilities.
All revenue management decisions – even selling one room for a single night – impact all the other decisions, since that room could be sold in combination with other nights for more overall revenue. There is a significant complexity arising from the network nature of the problem. For example, stay itineraries that are a combination of adjacent busy and non-busy nights may yield more overall revenue as opposed to stay itineraries that are a combination of only busy nights.
Decisions to accept or reject reservations must be made continuously, often up to a year in advance. This introduces uncertainty and a lack of complete knowledge at the time those decisions need to be made. As decisions need to be made in real-time in an uncertain environment, a complex forecasting and proactive mathematical optimisation process is needed; one that is only possible with AI-driven automated-decision revenue management systems.
In AI-based optimised systems, decision-making is highly dynamic, sophisticated and economical due to a computer’s ability to process large amounts of data and account for thousands of scenarios in a matter of seconds. They can produce optimal decisions in real-time in a network-wide sense while considering the uncertain nature of demand.
This is only possible with forecasting techniques that produce not only a forecast of average demand, but also the uncertainty of demand. Such a forecasting system feeds the decision optimisation system based on machine learning, as well as mathematical optimisation to maximise profit while managing the risks associated with the uncertain nature of the demand and the marketplace.
When good enough is NOT good enough
There is room for both traditional rule-based approaches and automated systems. The best system for your business depends on many factors, such as the complexity of your hotel, the amount of data you have access to, the structure of the underlying system delivering value, and how often the decisioning system needs to be updated.
Some hoteliers have decided that rule-based systems are “good enough”, especially as they restaff and retrain. But have they considered the most critical gaps, known or unknown, while understanding complex maths and behaviour-related anomalies? Commercial leaders must consider how to rectify these gaps while keeping in mind the staffing impacts and internal decisions they make.
The primary goal of forecasting is to identify the full range of possibilities, not a limited set of imagined certainties. Whether a specific forecast turns out to be accurate is only part of the picture – even a broken clock is right twice a day. Today’s guests behave in a different way to yesterday’s; tomorrows will look different again.
Above all, the forecaster’s task is to map uncertainty. In a world where our actions in the present influence the future, uncertainty is opportunity. Selecting an automated decision-making revenue management system will make the difference in a better understanding of the unknown.
IDeaS’ has a suite of revenue management solutions for hotels and other accommodation providers, designed to optimise profits across your revenue streams. Find out more at ideas.com