The HBCP is a collaboration between behavioural scientists, computer scientists and systems architects that started in 2017.

More than 100 behaviour change intervention evaluation reports are published every week; it is not feasible to extract all the key information from these reports by hand. This severely limits their use in building and testing models of behaviour that can, in turn, be used to predict intervention outcomes in novel scenarios.

The HBCP aimed to assess the feasibility of:

1. constructing a largely automated system for gathering information from reports of behaviour change intervention evaluations, and
2. using that information to predict intervention outcomes in novel scenarios.

Achieving these aims could transform behavioural science and dramatically accelerate progress towards developing more effective interventions.