Idea

The travel industry is comprised by a set of different stakeholders directly affected by tourist arrival flows at the destination where they are established. Many accommodation and food-beverage companies have developed strategies to maximize their income by trying to predict these flows at a daily rate, or even for circumscribed periods, like summer, weekends, or event dates. These strategies fall into the discipline of Revenue Management, where the primary goal is to sell the right product to the right customers, at the right time. In Revenue Management, forecasting is the essential element in order to develop more profitable pricing policies, since static accommodation pricing is no longer ensuring viable growth.

Objectives

ROSIE aims to build an AI-based Revenue Optimizing System which will integrate and analyze large amounts of data in order to forecast demand for the accommodation and food-beverage sector. The data-driven solution will exploit Big Data technologies along with Machine/Deep Learning algorithms to build models taking into account the entire demand/supply spectrum. This way, ROSIE aims to provide meaningful insights to the personnel of travel SMEs regarding the optimal prices throughout the year, without the need for advanced statistical training. The system will study dynamic pricing as price discrimination for different customer segments, thus maximizing occupancy rate, as well as other hotel Revenue Management KPIs (e.g. RevPAR).