Descripción del proyecto
Nuevo juego de herramientas para la modelización conductual a gran escala
Se necesitan modelos efectivos del comportamiento humano para predecir problemas y diseñar unas soluciones más sostenibles, seguras y saludables. Hoy en día, las nuevas tecnologías ofrecen información mejorada y basada en datos. Sin embargo, para lograr unos modelos matemáticos realistas aplicables en el mundo real, es necesario reconocer toda la complejidad del proceso humano de toma de decisiones. El proyecto SYNERGY, financiado con fondos europeos, diseñará nuevos modelos psicológicamente coherentes de los problemas del mundo real, ofreciendo un equilibrio entre suposiciones y conocimientos basados en datos. Para ello, combinará tres paradigmas fundamentales: métodos psicológicos (para dilucidar cómo se toman las decisiones), econométricos y conductuales (para comprender las influencias sobre los procesos de toma de decisiones) y basados en el aprendizaje automático (centrados en resultados concretos). Estos pueden contribuir a comprender los viajes y otros comportamientos durante una pandemia.
Objetivo
The SYNERGY project will unify three key paradigms for the mathematical modelling of human behaviour, namely: i) process models in psychology and cognate disciplines that seek to explain how decisions are made; ii) econometric and behavioural models that explain which factors influence the decision process and to what extent; and iii) data-driven (machine learning) methods that focus on the outcome of the decision process. The different aims and assumptions of these paradigms have resulted in very distinct strengths and weaknesses for each discipline. Only the synergy of the three will fulfil the promise of producing models that are behaviourally consistent, applicable to real-world problems, computationally tractable, and balance a priori assumptions with data-driven insights.
Integrating the three approaches into new Data-Driven Behavioural Models (DDBMs) is a novel, ambitious and highly complex undertaking, but one that is timely given the rapidly changing world, increasing use of models and big data for prediction, and growing interaction between humans and “intelligent machines” that require the latter to accurately predict human behaviour to enable safe and efficient use of AI. The proposed work will result in a paradigm shift for behavioural modelling, with impact in many application domains. SYNERGY will provide analysts with a powerful new toolkit that will allow efficient large-scale behavioural modelling on increasingly rich data while providing interpretable outputs and retaining important foundations in behavioural science.
Alongside major methodological contributions, the proposed research includes large-scale empirical work, applying the new DDBMs to real-world problems with implications for national policy. This includes case studies to understand and predict travel and other behaviour in a COVID-19 environment, and to establish the benefits that more behaviourally consistent AI routines for autonomous vehicles can have for road traffic safety.
Ámbito científico
Palabras clave
Programa(s)
Régimen de financiación
ERC-ADG - Advanced GrantInstitución de acogida
LS2 9JT Leeds
Reino Unido