Modelling dataset bias in machine-learned theories of economic decision-making.
Nat Hum Behav
; 8(4): 679-691, 2024 Apr.
Article
en En
| MEDLINE
| ID: mdl-38216691
ABSTRACT
Normative and descriptive models have long vied to explain and predict human risky choices, such as those between goods or gambles. A recent study reported the discovery of a new, more accurate model of human decision-making by training neural networks on a new online large-scale dataset, choices13k. Here we systematically analyse the relationships between several models and datasets using machine-learning methods and find evidence for dataset bias. Because participants' choices in stochastically dominated gambles were consistently skewed towards equipreference in the choices13k dataset, we hypothesized that this reflected increased decision noise. Indeed, a probabilistic generative model adding structured decision noise to a neural network trained on data from a laboratory study transferred best, that is, outperformed all models apart from those trained on choices13k. We conclude that a careful combination of theory and data analysis is still required to understand the complex interactions of machine-learning models and data of human risky choices.
Texto completo:
1
Colección:
01-internacional
Base de datos:
MEDLINE
Asunto principal:
Toma de Decisiones
/
Aprendizaje Automático
Tipo de estudio:
Health_economic_evaluation
/
Prognostic_studies
Límite:
Adult
/
Humans
Idioma:
En
Revista:
Nat Hum Behav
Año:
2024
Tipo del documento:
Article
País de afiliación:
Alemania
Pais de publicación:
Reino Unido