The availability of Big Data is deeply changing our approach to understanding and modeling economic and financial systems. Moreover it represents a huge business opportunity that can be exploited by having the right tools and concepts. In particular, the possibility of tracking the behavior of millions of consumers, investors, firms, etc., allows to overcome the traditional approach based on limited questionnaires and to answer questions such as: how does the aggregate behavior of markets emerges from the interaction of individuals? What is the community structure of individuals? Is it possible to infer the ecological interaction between "species" of individuals? How can we use individual based data to estimate macroeconomics quantities, such as prices, inflation, rates, unemployment and overcome the traditional methods?
The analysis of such databases requires the development of ad hoc inference techniques for high dimensional data and suitable visualization tools, also to provide decision makers (policy makers as well as business people) with tools for more informed decisions. The use of complex network theory is of paramount importance to model the interaction between individuals or companies, as well as to visualize the dependence structure (synchronous, lagged, or causal) of economic or financial variables.
Finally, the use of exogenous information, as the one conveyed by news, tweets, blogs, etc can provide a significant additional explanatory value. To this end it is important to cross of individual entities with semantic and sentiment analysis of texts relevant for the considered system.
The members of SoBigData have a consolidated experience in the analysis and modeling of economic and financial systems by using Big Data, complex network theory, and computational agent based modeling.