Predicting regime shifts in social systems modelled with agent-based methods

We investigate the possibility to apply a method of calculus analytics developed for predicting critical transitions in complex systems to social systems modelled with agent-based methods (ABMs). We introduce this method on the example of an equation-based modelled system and subsequently test it-to our knowledge for the first time-on ABMs. Our experiments show that the method may have wide applicability in the analysis of social systems. The method can help to approximate abrupt and thus unpredictable regime shifts, even though it may be constrained by stochastics and require a bit more experimentation in selecting suitable variables for making it work in ABMs.