Fully Data-driven but Interpretable Human Behavioural Modelling with Differentiable Discrete Choice Model
This addresses the problem of reducing reliance on expert domain knowledge for discrete choice models in human behaviour analysis, offering an incremental improvement with automated interpretability.
The paper tackles the challenge of fully automated but interpretable modelling of complex human behaviours by introducing the differentiable discrete choice model (Diff-DCM), which estimates interpretable closed-form utility functions from data without prior knowledge, achieving estimations within tens of seconds on a laptop.
Discrete choice models are essential for modelling various decision-making processes in human behaviour. However, the specification of these models has depended heavily on domain knowledge from experts, and the fully automated but interpretable modelling of complex human behaviours has been a long-standing challenge. In this paper, we introduce the differentiable discrete choice model (Diff-DCM), a fully data-driven method for the interpretable modelling, learning, prediction, and control of complex human behaviours, which is realised by differentiable programming. Solely from input features and choice outcomes without any prior knowledge, Diff-DCM can estimate interpretable closed-form utility functions that reproduce observed behaviours. Comprehensive experiments with both synthetic and real-world data demonstrate that Diff-DCM can be applied to various types of data and requires only a small amount of computational resources for the estimations, which can be completed within tens of seconds on a laptop without any accelerators. In these experiments, we also demonstrate that, using its differentiability, Diff-DCM can provide useful insights into human behaviours, such as an optimal intervention path for effective behavioural changes. This study provides a strong basis for the fully automated and reliable modelling, prediction, and control of human behaviours.