The socio-economic system is a paradigm which can be defined as complex because behaviour change of free agents can result in other individuals and organisations experiencing chaotic dynamics, non-linear interactions and other cascading effects. To embrace sustainability in such a paradigm requires the adoption of emerging technologies that can lead to the next quantum leap including the big data platform. Big data provides us with a stream of new and digitized data exploring the interactions between individuals, companies and other organizations. However, to understand the underlying behavior of social and economic agents, organizations and researchers must manage large quantities of unstructured and heterogeneous data. To succeed in this undertaking requires careful planning and organization of the entire process of data analysis, taking into account the particularities of social and economic analyses such as the wide variety of heterogeneous sources of information and the existence of strict governance policy.

In recent years, many tools for both qualitative and quantitative models have been developed to describe and better understand complex systems. These tools include stochastic and dynamic systems, multivariate statistics, network models, social network analysis, inference and stochastic processes, fuzzy theory, relational calculus, partial order theory, multi-criteria decision methods and other tools which have been widely used to address problems in socio-economic systems. Traditional quantitative methods for acquiring socioeconomic data are limited in their ability to examine the complexities of socio-economic systems. Therefore, big data collected from satellites, mobile phones, and social media, among other data sources, allow researchers to build on and sometimes replace traditional methods providing greater frequency and timeliness, accuracy and objectiveness as well as defining sustainable models.

This Special Issue invites original research and review papers discussing complex socio-economic, financial and environmental problems, with a particular focus on the development and applications of new quantitative methods and models which combine new techniques in AI and big data analytics.

Potential topics include but are not limited to the following:

• Geospatial modeling and machine learning
• Intensive longitudinal data analysis with big data
• Multilevel modeling techniques
• AI based network analysis
• Big data based causal inference
• Visualization and scientometric analysis
• Econometrics and demographic techniques
• Machine learning and fuzzy theory
• Complexity and simplicity
• Reducing complexity to simplicity
• Equilibrium or studying attractors
• Non-linear dynamics
• Self-organizing dynamics
• Survival not optimality
• Co-emergence of structure, beliefs and patterns of behavior