Socioeconomic Modelling and Prediction with Machine Learning

Dear Colleagues,

The socioeconomic context is formed by the sum of multidisciplinary relationships that occur between different areas. These include: (1) The biophysical environment, the resources, materials, and natural processes that enable life support and the products in the transformation processes; (2) the system of production and consumption, characterizing the industrial society and the economic and commercial transactions that make up modern civilization; and (3) the cultural environment, comprised of values and belief systems that are supposed to shape lifestyles and prioritize a series of social aspirations. In brief, socioeconomics is measured by sustainable results of human evolution.

On the other hand, Machine Learning (ML) comprises algorithms that automatically adapt their parameters to model data. Such models can classify, adjust or clusterize the samples in the data, through analysis of the data features. The model is built from a training set of the data, and after fitting this set it can be used to predict the behavior of new data. The learning capacity of ML is measured using a validation sample, which is a test set to check for the generalization of the fitting ability. ML is efficient when handling a large amount of data and complex structure or nonlinear spatial/temporal behavior, and is robust against noise.

ML has been applied to a wide range of fields, including hard sciences, where the data are usually in a numerical scale, but also in social sciences, wherein most of the data are either categorical or very heterogeneous for each sample, presenting many gaps in information. In this Special Issue, we propose a fusion of the techniques of ML with other forecasting methods usually applied to socioeconomics.

Nevertheless, even if the result of forecasting is relatively imprecise, the consequences of predicting a socioeconomic disaster—for instance, war, a climate change, a pandemic, or a volcanic eruption—through ML is highly beneficial. Hence, in this Special Issue we propose a fusion of the techniques of ML with other forecast methods usually applied to socioeconomics. The present issue of Sustainability is dedicated to publishing works which use ML models, including Bayesian classifier, Genetic Algorithms, Neural Networks, K-Near-Neighbors, Random Forest, Support Vector, etc., to forecast social phenomena, wherever it can be useful to the sustainable development of humanity.

a) Focus:

This Special Issue aims to communicate advances in the application of ML to socioeconomic complex phenomena in the context of sustainable development. It will help to connect the theoretical and technical scientific community working on data forecasting, to allow a cooperation between engineers, physicists, mathematicians, sociologists, economists, geologists, biologists, environmental scientists, and others concerned with human sustainable development.

b) Scope:

We welcome papers on any of the following subjects:

• ML applied to forecast climate effects.
• ML applied to housing, renting, and the real-estate market.
• ML applied to the touristic impact problem.
• ML applied to the migration flows.
• ML applied to renewable energy resources.
• Forecasting of the effects of pandemics in the sustainable development.
• Forecasting of the role of finance market in world sustainability.
• Forecasting of conflicts, war, and peace.
• Forecasting of the relationships of seismic movements and sustainability.
• Forecasting of human rights dynamic evolution.
• Forecasting of deforestation and recycling.
• Theoretical advances on Machine Learning models inspired in sustainability.

Prof. Dr. David Dominguez
Dr. Mario González-Rodríguez
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sustainability is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• machine learning
• sustainable development
• climate change
• neural networks
• house and rent
• pandemics forecast
• seismic forecast
• war forecast
• migration forecast