REACH will facilitate the creation of secure and trusted multi-stakeholder data value chains (DVCs). Incubated startups & SMEs performance will depend on their access and use of key strategic resources, such as the latest cutting edge tools and actual data.

Data Providers, among which is Play&go experience, and Digital Innovation Hubs (DIHs) have outlined a set of challenges to be tackled by the incubated startups and SMEs, linked with their datasets available. These Data Providers propose their business challenges and offer, secure and controlled access to their proprietary data sets for startups & SMEs to use when targeting these challenges. Data Providers engagement drives and validates the creation of new data value chains and solutions. This opens horizons for new partnerships and creation of new data value chains across diverse cross-sector data and solution providers.

Play&go experience has developed a platform to create customized apps that improves the visitor’s experience, based on gamification, geolocation and augmented reality. With geolocated data we provide the visitor information of interest getting more interaction, fun and immersion, in mixed reality.

Tourism & Entertainment challenges in REACH Incubator

1.- Sustainable mobility model for events and tourist destinations

Summary of the challenge

The goal is the generation of a sustainable mobility model for cities, both for businesses that want to know where visitors move, and for the administration in the face of urban planning and mobility management.

Description of the global challenge
Tourist cities have crowding problems in certain areas and times, usually associated with festivities and events of interest. Likewise, mobility and traffic problems occur in these situations, which directly affects pollution.
Through this challenge, it is proposed to identify and visualize in a simple and intuitive way where and when these agglomerations have occurred around Points of Interest and tourist resources in large events in different cities.
This information will help to promote a certain behaviour among visitors, causing them to move to less saturated areas and favouring the decentralization of tourists.
The challenge proposed is the generation of a sustainable mobility model for cities, both for businesses that want to know where visitors move, and for the administration in the face of urban planning and mobility management. The model must consider all these aspects, as well as other external data sources, so that this model can be extrapolated to other cities and other similar events.

Sub-challenges composing this experiment
Events/Destinations (objectives)
Events/Destinations (ratings)
The available Dataset is First Data Party, so they can be added to other types of open data (e.g. statistical and mobility data from the INE, etc.) or from companies (telephony and banks) to improve the model and obtain behaviour patterns in other scenarios spatial or temporal in any economic sector.

Expected global results
It is expected to obtain the mobility of tourists and the areas with the most mobility and the highest rated POIs.
The result will be displayed in the form of a dashboard with maps and interactive graphics that allow the results to be viewed and their evolution predicted.

2.- Analyze the behavior of tourist and increase their average spending

Summary of the challenge
The main goal is to identify the behaviour of tourists who visit the destination and define what extra products or services can be offered to increase their average local spending.

Description of the global challenge
It is intended to go a step further in the knowledge of the mobility of the tourists, increasing the complexity of the result to be obtained and above all focusing it on an economic benefit.
By adding other external sources of information, many more data can be obtained that affect tourist activity in cities. Geolocation is configured as the identifier that unites all this data and, from here, a complex system of geolocated information layers of a city can be made available.
The objective is to identify the behaviour of tourists who visit the destination (demand analysis) and define what extra products or services can be offered to increase their average local spending (supply analysis), to offer a global vision of the situation, identifying the areas where there is a lower balance between supply and demand, also identifying which factors are the cause of both situations.
For this, it is necessary to identify various data sources, analyse them and prioritize those that are most relevant to tourists, so that a Geographic Information System is generated that, through Machine Learning and Artificial Intelligence techniques, is capable of generating predictions about the future behaviour of tourists based on the development of certain areas and services that contribute to increasing their average spending in the destination.

Sub-challenges composing this experiment
This challenge is composed of 2 sub-challenges:
Analysis and profiling of the tourist
Demand for non-existent services

Expected global results
The expected results are to identify the 3 main drivers of tourist behaviour
Make a prediction of local development of resources, products and services that foresees an increase of 10% in average spending.

2.1.- Analysis and profiling of the tourist

Summary of the sub-challenge
The aim is to predict and identify tourists interests when visiting a city.
Description of the challenge
The sub-challenge consists in identifying, collecting, analysing, and selecting the data sources that may be most relevant in the city when it comes to analysing tourist behaviour.
From here, all these data should be integrated and, using smart location, search for the most relevant variables and try to generate a model that explains the behaviour of said tourist in the city.
Based on the tour made by the tourist, the aim is to identify habits such as where they shop, where they eat, what other attractions in the city they visit, etc. In this way, the most visited areas of the city can be identified and why, so that other areas are sought in which similar variables exist or can be promoted that favour the movement and consumption of tourists in these new areas.
As they are complex, multivariate and predictive analysis, it will be necessary to use Machine Learning and Artificial Intelligence techniques in order to generate these predictions, identify patterns and establish models.
Data to be used
Events/Destinations (objectives)
Events/Destinations (ratings)
It would be advisable to combine these datasets with other data that help to achieve it, such as hospitality, commerce, transport, social networks, credit card spending, origin of tourists, areas from which access the city, etc.
Expected outcomes
To identify the 3 main drivers of tourist behaviour.
To discover the 3 main areas of the city that attract them.
To discover the 3 areas with the most potential to do so based on the previous points.

2.2.- Demand for non-existente services

Summary of the sub-challenge
The objective is to identify what services, not present in current offer, could offer value to a tourist by knowing the route and the behaviour of the tourist.
Description of the challenge
This sub-challenge consists in knowing where, when and what products and services tourists consume to identify those that could offer value and are not present. In this sense, it is necessary to delve into the datasets from the supply side, that is, to identify what local businesses are offering in each area of ​​the city.
The search for new non-existent services or services that have a high profitability, which can be incorporated into the destination service offer, the use of information sources from other similar events and destinations around the world will be needed.
As they are complex, multivariate and predictive analysis, it will be necessary to use Machine Learning and Artificial Intelligence techniques in order to generate these predictions, identify patterns and establish models.
Data to be used
Events/Destinations (objectives)
Events/Destinations (ratings)
It would be advisable to combine these datasets with other data that help to achieve it, such as hospitality, commerce, transport, social networks, credit card spending, origin of tourists, areas from which access the city, etc.
Expected outcomes
To identify opportunities for new businesses or services in the different areas of the city.
It would be necessary to know which are the 3 most balanced and profitable areas of the city and what is the type of services offered.

OPEN CALLS