Latest Post

Our latest preprint, titled “Attention-based dynamic multilayer graph neural networks for loan default prediction”, introduces a novel model that could enhance the accuracy of credit risk assessments. Credit Scoring and Correlated Default The inspiration for this work comes from our previous studies, which clearly show that borrowers are not isolated entities but part of a […]

Our values


Following best practices in the field.


To the extent possible, all science we produce should be easily deployable by others.


We seek to be better, both individually and as a group.


We embrace diversity, both internally and in our research. We work across the world to serve communities and we seek to eliminate structural biases and support financial inclusion worldwide.


We quickly accept and include new ideas in our work. We also quickly discard ideas that do not pan out and look for novel ways to solve our problems.