Realizing the Potential of Agent-Based Social Simulation
Facts
- Contact person:
- Paul Davidsson
- Financer:
-
- WASP-HS: The Wallenberg AI
- Autonomous Systems and Software Program – Humanities and Society
- Responsible at MaU:
- Paul Davidsson
- Project members at MaU:
- Time frame:
- 01 January 2021 - 31 December 2026
- Faculty/department:
- Research environment :
- Research subject:
About the project
Computer simulation is established as a method for investigating the behaviour of a system under certain conditions. When real-world experiments are too costly, time-consuming, impossible or impracticable, simulation provides an alternative approach for controlled and systematic investigations. The insights from such experiments cannot only be used by scientists but more importantly by decision-makers to consider the advantages and disadvantages of possible policies or actions before they are implemented. There are many different simulation methods, but typically they have problems to model complex human behaviour and social interaction in a realistic way.
Agent-Based Social Simulation (ABSS)
As an attempt to address these issues, the paradigm of Agent-Based Social Simulation (ABSS) has been introduced. ABSS is a very powerful simulation paradigm that integrates AI in the modelling of human behaviour and social interaction. The relevant properties of each individual, as well as its decision-making and actions, are explicitly modelled. However, although there are a few successful applications of ABSS that have informed actual decision-making, e.g., for electricity markets or emergency management, the majority have been providing useful insights to social scientists. We argue that the full potential of ABSS yet has not been realized in terms of providing support for societal decision-makers. One problem has been the scalability of ABSS, which often works great when the number of individuals is in the thousands but not in the millions. Moreover, the models of human behaviour used in current ABSS are rather homogenous, often not taking into account the actual variations in populations, e.g. age, gender, ethnicity, cultural characteristics and habits.
In order to provide support for decision-making in a responsible way that is ethically sound, fair and inclusive, the modelling of this diversity is crucial. Due to the variety of existing simulation models, it is not only challenging for decision-makers and analysts to find appropriate models but also to assess their strengths and weaknesses. This oversupply in similar models can lead to insecurity regarding which model to use and trust. To overcome this issue, one approach would be to combine several models to multi-model ensembles to provide better and more robust results and reduce uncertainty compared to each individual model.
The proposed project concerns removing the barriers that currently hinder ABSS to be used broadly by societal decision-makers and analysts. This includes the investigation of how the strengths of ABSS models can be combined with other models for investigating social behaviour to novel and more mature models that allow for comprehensive and confident simulations of societal phenomena. The project will contribute to creating synergies between different disciplines and paradigms, and the generation of more sound simulation results.