In order to extract the full value of data, it is necessary to classify, filter and cross-reference it through analytics processes that help us draw conclusions, turning data into information and knowledge. Traditionally, data analytics is divided into 3 categories:

• Descriptive analytics, which helps us to understand the current situation, what has happened to get there and why it has happened.
• Predictive analytics, which aims to anticipate relevant events. In other words, it tells us what is going to happen so that a human being can make a decision.
• Prescriptive analytics, which provides information on the best decisions based on a series of future scenarios.  In other words, it tells us what to do.

The third report in the "Awareness, Inspire, Action" series focuses on the second stage, Predictive Analytics. It follows the same methodology as the two previous reports on Artificial Intelligence and Natural Language Processing.

Predictive analytics allows us to answer business questions such as: Will we suffer a stockout, will the price of a certain share fall, or will more tourists visit us in the future? Based on this information, companies can define their business strategy, and public bodies can develop policies that respond to the needs of citizens.

After a brief introduction that contextualises the subject matter and explains the methodology, the report, written by Alejandro Alija, is developed as follows:

• Awareness. The Awareness section explains the key concepts, highlighting the three attributes of predictive analytics: the emphasis on prediction, the business relevance of the resulting knowledge and its trend towards democratisation to extend its use beyond specialist users and data scientists. This section also mentions the mathematical models it makes use of and details some of its most important milestones throughout history, such as the Kyoto protocol or its usefulness in detecting customer leakage.
• Inspire. The Inspire section analyses some of the most relevant use cases of predictive analytics today in three very different sectors. It starts with the industrial sector, explaining how predictive maintenance and anomaly detection works. It continues with examples relating to price and demand prediction, in the distribution chain of a supermarket and in the energy sector. Finally, it ends with the health sector and augmented medical imaging diagnostics.
• Action. In the Action section, a concrete use case is developed in a practical way, using real data and technological tools. In this case, the selected dataset is traffic accidents in the city of Madrid, published by the Madrid City Council. Through the methodology shown in the following figure, it is explained in a simple way how to use time series analysis techniques to model and predict the number of accidents in future months.

The report ends with the Last stop section, where courses, books and articles of interest are compiled for those users who want to continue advancing in the subject.

In this video, the author tells you more about the report and predictive analytics (only available in Spanish).

Below, you can download the full report in pdf and word (reusable version), as well as access the code used in the Action example at this link.

The pandemic that originated last year has brought about a significant change in the way we see the world and how we relate to it. As far as the education sector is concerned, students and teachers at all levels have been forced to change the face-to-face teaching and learning methodology for a telematic system.

In this context, within the framework of the Aporta Initiative, the study "Data-based educational technology to improve learning in the classroom and at home", by José Luis Marín, has been developed. This report offers several keys to reflect on the new challenges posed by this situation, which can be turned into opportunities if we manage to introduce changes that promote the improvement of the teaching-learning process beyond simply replacing face-to-face classes with online training.

The importance of data to improve the education sector

Through innovative educational technology based on data and artificial intelligence, some of the challenges facing the education system can be addressed. For this report, 4 of these challenges have been selected:

·      Non-presential supervision of assessment tests: monitoring and surveillance of evaluative tests through telematic resources.

·      Identification of behavioral or attention problems: alerting teachers to activities and behaviors that indicate attention, motivation or behavioral problems.

·      Personalized and more attractive training programs: adaptation of learning routes and pace of students' learning.

·      Improved performance on standardized tests: use of online learning platforms to improve results on standardized tests, to reinforce mastery of a particular subject, and to achieve fairer and more equitable assessment.

To address each of these four challenges, a simple structure divided into three sections is proposed:

1.     Description of the problem, which allows us to put the challenge in context.

2.     Analysis of some of the approaches based on the use of data and artificial intelligence that are used to offer a technological solution to the challenge in question.

3.     Examples of relevant or highly innovative solutions or experiences.

The report also highlights the enormous complexity involved in this type of issues, so they should be approached with caution to avoid negative consequences on individuals, such as cybersecurity issues, invasion of privacy or risk of exclusion of some groups, among others. To this end, the document ends with a series of conclusions that converge in the idea that the best way to generate better results for all students, alleviating inequalities, is to combine excellent teachers and excellent technology that enhances their capabilities. In this process, open data can play an even more relevant role in improving the state of the art in educational technology and ensuring more widespread access to certain innovations that are largely based on machine learning or artificial intelligence technologies.

In this video, the author tells us more about the report:

Winning projects of the 4th Castilla y León Government Open Data Competition

Open data is an increasingly used resource for the training of students at different stages of the education system and for the continuous training of professionals from all sectors. There is already little doubt about the growing importance of all the skills related to data analysis and processing in relation to almost any knowledge discipline. Similarly, skills related to visualization and the construction of stories based on the conclusions drawn from any data analysis or modeling are increasingly needed to complement and extend the ever-necessary skills to communicate and present results of any kind of work.

Throughout the process of training professionals related to data science and artificial intelligence, open data is a valuable resource for gaining practical experience with the techniques and tools that are common in the profession. However, the effects that the use of data, usually open, has on the learning of other subjects, on the acquisition of other types of skills and even on the motivation of students towards learning, are also beginning to be appreciated.

As early as 2013, research that conducted a detailed quantitative comparison of different educational approaches adopted by 39 schools in New York City showed that the use of data to guide the educational programme was one of the five main policies that had an effect on improving academic performance.

Although the use of open data in the classroom has not been widely studied, the limited research conducted so far suggests at first glance that there is a lack of awareness of open data among educators. While we do not have a consolidated understanding of the effect of the use of open data in educational settings as it is not currently a widespread educational resource, there does appear to be a set of early adopter educators who make substantial use of open data in their teaching programmes.

The research "The use of open data as a material for learning" by the Institute of Educational Technology is based on the qualitative analysis of the experience of a group of these pioneering educators to draw a number of conclusions about the value of using open data in teaching.

One of the starting points is that open data does not seem to offer completely new educational or pedagogical methodologies, but rather its use complements existing concepts of teaching and learning such as research-based or project-based learning or personalisation of learning. Two conclusions stand out in this respect:

1. Open datasets used as part of learning projects in any subject are usually relevant to the learner, either because they describe issues in their geographical or social environment, or because they relate to current issues or their own hobbies. Research shows that the mere use of these datasets that arouse student curiosity during the learning of any concept has positive effects on the motivation of students to go deeper into the subject and appreciate its usefulness.

2. The use of open datasets offers the possibility to propose more advanced activities without increasing the difficulty of the training programme. Examples are cited in the research ranging from the use of open data to support the statistics training of high school students to the use of open scientific databases in the area of genomics to support the teaching of bioinformatics concepts. In this way students can acquire more advanced knowledge and skills that would otherwise probably only have been produced in the field of professional activity or would have been discarded due to insufficient time in the programme. This effect, especially at higher education levels, would also contribute to closing the gap between the education system and professional practice.

Although their effect has not yet been studied, open data competitions are another vehicle for channelling the practical training of students and for creating new educational resources. Increasingly, universities or secondary schools are encouraging teams to participate in regional or national open data competitions as an activity within certain subjects. Some competitions, such as the Castilla y León open data competition, even have a special category with a corresponding prize reserved for the participation of students.

Along the same lines, Barcelona City Council has been organising the Barcelona Dades Obertes Challenge for four years, which aims to bring the benefits of open data closer to the public and to promote its use in the city's educational centres. The challenge combines competition between schools, which have to develop a data-based project, with a specific training plan on open data for teachers, so that they can guide their students.

The fact that there is no more widespread use of open datasets in educational programmes can be attributed to factors such as the lack of teacher training or the difficulty in adapting existing data. Most open datasets come from professional environments such as scientific research or public service administration and learners and educators may not have the literacy or resources to take advantage of them even though tools are emerging that simplify some of the complexities of working with open data. In this regard, a stronger relationship and joint work between educators and learners and dataset producers could also encourage the deployment of more learning programmes.

This is why there are interesting initiatives such as UDIT (Use Open Research Data In Teaching) launched in 2017 with the aim of encouraging and helping higher education teachers to incorporate open research data and other open science concepts into their teaching to improve the learning process.

The International Open Data Charter already recognises the importance of engaging "with schools and higher education institutions to support further open data research and to incorporate data literacy into education programmes". The value of open data in the learning process has not yet been sufficiently explored. As an example, the usual discourse of the open data community always highlights the potential economic and social value of reuse, but not so much the potential of its use in education.

Content prepared by Jose Luis Marín, Senior Consultant in Data, Strategy, Innovation & Digitalization.

The contents and points of view reflected in this publication are the sole responsibility of its author.

The open data ecosystem returned to full strength after the summer. During these autumn months, numerous initiatives have emerged to promote the use, reuse and dissemination of open data. They have been very productive weeks, so it has been impossible to collect them all in one post. However, we present you a small selection that will surely be of your interest.

Tools and applications to access more open data

We begin the review of the new developments that have emerged this fall in the open data ecosystem with the initiatives that have been encouraged to make available public data through various tools. We present you some of them:

• Castellón Provincial Council has presented its open data observatory, a great platform of updated information that includes indicators with the actions carried out by the Council to address the COVID, an area of good practice, a section with information on the Council of Reusers and the Provincial Council's Open Data Portal.
• Valencia City Council has renewed its Geoportal with the Smart City app, which shows thousands of open data of the city in fields such as mobility, wifi points, gardening, markets, sports or cultural elements.
• The University of Extremadura has made public its new research portal. The portal automatically collects the scientific and transfer production of the researchers without requiring any effort from the user.
• Ponferrada City Council, together with the company Rendytel, has presented a project to measure air quality in public spaces and buildings using technology based on IoT devices, which provide open data to all citizens. Through their mobile phones, users can find out the state of the air and the level of ventilation in real time and, therefore, assess the possible risk of contagion of Covid-19.

Although this is not a new initiative, we would like to take this opportunity to highlight that the Junta de Castilla y León has received the NovaGob Excellence Award for its work on transparency when displaying data on its portal.

Examples of reuse

Did you know that public bodies, in addition to continuing to open up their information, also continue to create services and products based on its reuse? Here are three examples from this fall:

• The University of Valladolid has developed the application 'Casual Learn', which is based on open data to help users learn art history. The application suggests learning tasks taking into account the interests and location of the user.
• Casual Learn was one of the winning projects in the 4th Castilla y León Open Data Competition, in this case in the category of Teaching Resources. In the Products and Services category, the winner was "Escovid19data", a collaborative collection of data from COVID-19 by province in Spain, while "Castilla y León en remoto" took first place in the ideas category and "Coverage of coronavirus diagnostic tests in Spain" in the data journalism category.
• Onda Town Council has presented an app which offers information on free parking spaces, traffic conditions, environmental parameters and pharmacies on duty. This application is part of the Onda Smart City project, a project which turned out to be the winner of the 12th Aslan Awards, as we reported a few months ago.

In addition to public bodies, we also want to highlight the work done by the four young Basques who have created Dataseeds, a platform at the service of European agricultural SMEs to offer a large amount of open data and facilitate their evolution towards a green transition. With their solution, they have come third in the "A European Green Deal" challenge in the EU Datathon 2020.

Events, courses and publications aimed at disseminating open data

But if there is a reason why autumn has stood out, it has been because of the great number of events, competitions, webinars and other activities aimed at promoting open data.

• Este otoño Asedie ha estrenado nuevo blog. Entre los contenidos que aborda destaca la transformación digital, la inteligencia artificial o los datos abiertos, siempre con el foco puesto en las empresas infomediarias.
• La Iniciativa Aporta acompañó a Databeers Málaga en su primera edición online, que este año estuvo dedicada a los datos abiertos de Copernicus. Si quieres conocer más sobre nuestra participación en esta jornada, puedes hacerlo aquí.
• The Government Obert Chair promoted by the Polytechnic University of Valencia, has transferred to the participants in the Autumn Camp of Transparency and Data Management, the foundations for the understanding of concepts related to open data management. In addition, the Valencian Community has announced during this period that it will train companies and professionals in smart city technologies through the project 'Ciudades conectadas y habitable'.
• Open data not only serves to bring applications to life, but also to enrich journalistic and literary works. The Generalitat de Catalunya has published the book "Open data and artificial intelligence, tools for gender equality". This writing allows us to reflect on how open data is also a key element in the fight against gender discrimination.
• Open data competitions have been a constant throughout the autumn: the Aporta Challenge, the Basque Country Open Data competition, BiscayApp...

Some international proposals

At the international level, some very interesting initiatives have also emerged this autumn.

• The World Bank has launched an open water data portal to help countries make informed decisions that will lead to a water-secure world.
• During these months, the European Data Portal has organized different webinars to address the future of open data portals, where experiences, good practices and opportunities for action have been shown to ensure that open data portals remain useful for the community. These webinars will run until January.
• We end with an international news, but with a local component. Brussels awards a Spanish consortium Yoda, its new European project based on open data. This is the development of a platform for any European citizen to create their own personalized board where they can order different sources of information according to their interests.

These are just some of the most prominent examples that have emerged in the world of open data during the autumn months of 2020. However, if you know of any other news that may be of interest, please do not hesitate to mention it in the comments or send us an email to dinamizacion@datos.gob.es.

Climate change, air pollution and sea pollution. These are the 3 main environmental problems for Spanish citizens according to the latest Eurobarometer "Attitudes of European citizens towards the Environment", published in March 2020. The survey also highlights that 90% of the Spanish population considers to protect the natural environment important. Citizens want more action to be taken and believe that responsibility should be shared between companies, national governments, the EU and citizens themselves.

As with other sectors, such as education or health, open data can also help us to overcome environmental challenges. On the one hand, it provides us with detailed information to understand the situation and to be able to look for solutions. On the other hand, they serve to implement solutions that help us raise awareness and reduce our environmental footprint.

In its report "The Economic Impact of Open Data Opportunities for value creation in Europe”, ", the European Data Portal highlights that data can "contribute to reducing total energy consumption in Europe, increasing the use of sustainable energy sources, protecting biodiversity and raising awareness of CO2 emissions", as well as generating an economic impact of around 1€ billion. Let's look at some examples:

• Reducing energy consumption. Open data-based applications can serve as a tool to help households and institutions to understand and reduce their energy consumption. In this sense, the Regional Government of Castilla y León has launched an Energy Datahub that provides detailed and visual information on energy consumption in the more than 1,500 centres managed by the Regional Government: educational centres, health centres, administrative offices, hospitals, etc. The scorecard facilitates the disaggregated analysis by type of energy (electricity, gas, diesel) and by geographical location, allowing informed decisions to be made. According to the Board itself, thanks to the energy scorecard they have saved more than 12 million euros in electricity since 2015.
• Increase the use of sustainable energy. The 2018 EU directive on the promotion of the use of energy from renewable sources sets a target for the share of renewable energy in gross final consumption to be 32% by 2030. To help achieve this target, publicly available data on urban planning, use of public services or weather conditions can be cross-checked to create solutions that help make housing more sustainable. One example is Solarmap, which allows the profitability of a solar panel installation to be calculated for a specific location.
• Improving biodiversity: Changes in ecosystems can lead to mass extinctions of species and the limitation of available natural resources, which can affect not only our economy but also our own way of life. In this sense, open data serves as a basis for solutions that, for example, help us monitor various parameters of port waters (such as Environmental Control Panel), improve waste management (Punto limpio) or publicise noise pollution (MAdb).
• Raise awareness of air pollution and the reduction of CO2 emissions. Although, as we saw at the beginning of this article, we Spaniards are very aware of climate change, however, if we look at the individual habits of citizens, we see that there is still much to be done. Only 38% try to reduce their energy consumption, 28% choose less polluting forms of transport, and 36% buy local products. It is therefore necessary to continue raising awareness, for example through indicators of air quality in cities such as GV Aire. There is also a need for applications that promote the use of more efficient means of transport, such as bicycles or public transport (Barcelona metro bus rodalies bici).

You can find more examples in the applications section of datos.gob.es and in our environment section.

A large number of different data sources with different contents and formats coexist in an open data portal. It is therefore necessary to provide each file, resource or content on the network with a context or definition that allows people, and also machines, to interpret its meaning. This is where the concept of Linked data comes in.

Linked Data allows the web to be used as a single large global database. Following this publishing paradigm, data is available in context and interconnected for reuse. Linked Data emerged from the Semantic Web project inspired by Tim Berners-Lee, the father of the Web, from the need to introduce contextual information in the form of metadata on the Web.

The document "LinkedData as an open data model" briefly explains the basic concepts to understand how the semantic web and linked data works, such as the case of URIs or unique resource identifiers, ontologies or vocabularies that allow the description of relationships between them, to focus on how Aragon has implemented these technologies to develop different services, such as:

• The Interoperable Information Structure (EI2A), an ontology that homogenises structures, vocabularies and characteristics to respond to the diversity and heterogeneity of existing data within the Administration, within the framework of Aragon Open Data. The document explains some of the ontologies and vocabularies used for the development.
• The European Legislation Identifier (ELI), which allows online access to legislation in a formalised format that facilitates its reuse.
• The semantic infrastructure in Aragon Open Data, where the use of the Virtuoso tool for the storage of linked data stands out. The document explains the characteristics of this universal server, whose architecture allows the persistence of data in RDF-XML formats, among others. In addition, it explains how the bank that stores triplets in a native way for resources relationships works and shows examples of services of Aragon Open data that exploit these triplets of data as Aragopedia and Aragon Open Data Pool.

You can then download the full document (only available in Spanish).

This document is part of the series of educational materials and technological articles that Aragón open Data is producing in order to explain how they have deployed different solutions to respond to the needs for location, access and reuse of the different sets of data. You can complete your reading with another volume in the series: "How to implement CKAN: real case of the Aragon Open Data portal".

Aragon Open Data is one of the most active open data initiatives on the Spanish scene. In addition to the implementation, management and maintenance of an interoperable data catalogue, since its inception Aragon Open Data has carried out actions to bring the culture of open data closer to citizens, companies and all types of organisations. These initiatives include the development of services to offer the data and facilitate its reuse in a simple way such as Aragopedia, Open Social Data or the recent Aragón Open Data Focus (more information available in this interview).

Given the knowledge that they hold, it is not surprising that they have begun to develop educational materials and technological articles with the aim of explaining how they have deployed different solutions to respond to the needs of localisation, access and reuse of the different sets of data.

Below is one such material, which focuses on explaining how they have implemented the CKAN software solution to improve the availability of data on the portal.

CKAN as an open data management software solution in a real case for the Aragon Open Data portal

CKAN is a free, open-source platform developed by the Open Knowledge Foundation for publishing and cataloguing data collections. Due to its free and open nature, as well as its rapid implementation, it has become a worldwide reference for the opening of data.

Since its birth in 2012, Aragon Open Data has bet on CKAN technology for the management of its open data system. The document "CKAN, cornerstone for the management of an open data system" shows us how its architecture works and serves as an example for other initiatives that want to implement a platform of this type.

The document describes the challenges they encountered when migrating the original platform to a higher version and how they solved it by building a client application. This process resulted in the current architecture of the portal, which is shown in the figure below:

The CKAN backend is developed entirely in Python, with its own Javascript front end, and allows the deployment of a layer of services that can be managed from an API, and the use of base plugins or extensions that provide additional functionalities to the platform. CKAN is supported by a PostgreSQL database, where the datasets it houses, its resources and other metadata required for the operation of the platform are stored, and makes use of Solr, a search engine that helps to speed up the location and availability of the datasets.

In addition to explaining this architecture, the document discusses the functionalities and extensions used in the customised CKAN instance, and how the set of components integrated into the platform: Angular, NodeJS, PostgreSQL and Solr coexist to provide data sets that are the basis for the development of open data services and solutions such as Presupuestos de Aragón or the already mentioned Aragón Open Data Focus.

CKAN incorporates an extension that supports RFD data serialisation which, in addition to allowing the exposure of linked data in formats such as RDF-XML or Turtle, is used to federate datasets that follow the DCAT specification of metadata, making CKAN a more versatile and appropriate platform for the publication of Linked Data, something that Aragon Open Data has also done as we can see in this other document.

You can download the document "CKAN as an open data management software solution in a real case for the Aragon Open Data portal" below (only available in Spanish). You can also complement your reading with these two additional articles:

• Automatic collection of open data: Explains how Aragon Open Data federates open data using a CKAN plugin.
• ELK architecture as an open data tool: Explains how Aragon Open Data uses an architecture based on the ELK technology stack (Elasticsearch, Logstash and Kibana).

Is it possible to find in the data the necessary help to solve the real problems that our society faces? While it is true that data alone cannot be transformed into food for the most disadvantaged, nor can it make weapons disappear in conflict zones or inequalities in the world, they are very useful when it comes to providing information on the causes that cause certain events or situations. Thanks to them, we can better assess the reasons and consequences of these situations, and act so that they do not recur.

Once, thanks to open data, we identify the causes that cause these types of events, we must take one more step: use this information to develop solutions and services that help us solve problems such as, for example, the lack of social inclusion of marginalized groups or inequalities caused by gender, economic or social issues.

When we speak of inclusion, we refer to the process by which both individuals and communities of people, such as migrants, refugees, socially disadvantaged groups or individuals, can interact and integrate in their communities in a satisfactory way and with the same opportunities.

Next, we will see some examples of the importance of open data when creating instruments and services that help the integration of this type of groups, focusing especially on the challenges that our country faces.

Problems related to inequality in Spain and digital solutions based on open data to solve them

Labor insertion

In a context where the health crisis is damaging our economy, it is essential to bring job opportunities closer to citizens. The open publication of job offers and courses, as the Basque Employment Service does through its Lanbide platform, is allowing many job web portals and training centers to add these offers to their catalog easily, promoting their dissemination and , therefore, the labor insertion of job seekers.

Depopulation of rural areas

Currently in Spain it is necessary to make users more visible and aware of the great depopulation problem suffered by some areas of our country, in which its inhabitants have less and less social resources, which sometimes leads to increasing their isolation.

Tool such as "La España Vacía", which consists of a series of interactive maps that show the Spanish demographic evolution, help us to make visible and understand the problem, while platforms such as Plan Repuebla can serve to attract businesses and new inhabitants to areas with lower population density.

Gender inequality 

There are platforms that function as a great channel of awareness and support for women victims of sexist violence, offering testimonies and analysis of the current situation. This is the case of Desprotegides, a portal created in Catalonia that seeks to make visible the serious problem of sexist violence suffered by thousands of women in the world today, in this case with updated data on the number of victims in the Catalan community.

One step further goes the Data COVID Gender project created by the Barcelona Open Data Initiative together with the Gender and ICT group (GENTIC) of the Internet Interdisciplicary Institute (IN3). The project consists of analyzing the impact that gender and occupational segregation have on the prevalence of the coronavirus. It has been one of the 15 proposals chosen by the Catalan Health Quality and Evaluation Agency (Aquas) of the Department of Health to carry out research in data analytics on the incidence of SARS-CoV-2 and Covid-19 in Catalonia.

Integration of people with disabilities

In recent years, simple applications that, using open data, provide useful information about the environment. In this article you can find different applications created by companies and citizens, but also public services are working in this regard. As an example, the city of Murcia has launched a free application that allows people with hearing disabilities to receive information about municipal services and carry out the procedures they request by way of videoconference through a smartphone.

Relevant information about the coronavirus for risk groups

Curvaenaragon.com is a web page developed by the Government of Aragon whose main objective is to show updated information on the situation of Covid-19 in the autonomous community, breaking down the data by the different provinces (Huesca, Zaragoza and Teruel).

This website allows all citizens who reside or have to travel to Aragon to consult the evolution of the pandemic in the area, especially for the risk groups that are most vulnerable to this pathology.

In short, there are more and more applications and technologies that, thanks to open data, allow us to obtain useful information about the environment in order to offer solutions to problems such as inequality, disability, poverty or violence, among others.

These are just some examples of applications that use open data to favor the eradication of inequality, but if you know of any other that fulfills a similar function, do not hesitate to register it on our portal or send us an email to contacto@datos.gob.es

Content elaborated by datos.gob.es team.