Data-driven method simulates individual decisions in cooperation games
A data-driven heuristic-ensemble method for behavioural inference in collective-risk dilemma experiments
Computers and Society
Summary
People often face situations where working together matters, like in climate change challenges. This paper explains a new way to understand and mimic how individuals make choices in such group problems by using actual data about their past actions. The authors create a system that uses simple decision rules seen in real life and combines them to predict future behaviors without guessing any unknown details. This method can also help test scenarios that haven't been tried in real experiments yet.
What this means in practice
- •For game designers: Generate realistic player decision models for social dilemma games using data-driven behavioural heuristics.
- •For policy simulation teams: Simulate citizen responses to collective-risk policies by reproducing observed decision patterns without assumptions.
Authors
Marc Sadurní, Martín F. Díaz, Josep Perelló, Miquel Montero
Abstract
The collective-risk dilemma has become a paradigm for studying cooperation in a wide variety of social experiments, initiatives that generate increasingly rich datasets describing individual actions over successive decision-making processes. Beyond the purely descriptive analysis of such empirical datasets, a methodological framework is required to interpret and reproduce the observed dynamics, a scheme that may be skewed by exogenous biases. Here, we introduce a data-driven, non-parametric method for simulating individual decisions together with a validation protocol for assessing the fidelity level of the outcomes they generate. Our methodological contribution is based on an empirical heuristic ensemble: agents are represented by a finite set of behavioural heuristics, probabilities conditioned on different observable features of the game state, endowed with a hard-voting arbitration that determines their per-round final decisions. This reproducible generative framework allows for behavioural inference in different collective-risk dilemma setups: Behavioural heuristics are seeded directly from empirical data assessing conditional probabilities, without a priori assumptions; a plurality vote with uniform random tie-breaking resolves between competing heuristics each round, adding no free parameters; validation follows a pattern-oriented approach, comparing synthetic and empirical macro-indicators against single-heuristic and uniform-random baselines; synthetic data generated allow exploration of scenarios or experimental setups that have not been empirically realised; as a worked example, we instantiate our methodological approach on the xAire citizen science collective-risk dilemma experiment run in Barcelona.