Egor Kraev



Egor Kraev



December 1st - 10:15am

Keynote: AI at Transferwise - the right tools for each task

At TransferWise, our mission is money without borders - instant, convenient, transparent and eventually free. To achieve that, we need to build AI functionality in a surprising number of different domains, from customer service to fraud detection and optimal sourcing of cash to satisfy our clients' needs.
I will go over some of these usecases, and the choice of the right method in each case: when do we use a gradient boosting library (and which one), a neural network, a good old LPQC-MI optimizer, or a combination - and why.
The landscape of freely available AI and big data tools has greatly changed over the last several years, with certain problems having a clear 'winner' methodology, and others requiring a much more case-by-case approach. I'll go over some of the more mature tools and their strengths and weaknesses.


Egor first learned mathematics in the Russian tradition, then continued his studies with an MSc at ETH Zurich and a PhD at the University of Maryland. Egor has been doing data science before it was a thing, including economic and human development data analysis for nonprofits in the US, the UK, and Ghana, and 10 years as a quant at UBS then Deutsche Bank. Following this decade's explosion in AI techniques, Egor was Head of AI at Mosaic Smart Data Ltd for three years, and now is bringing the power of AI to bear at TransferWise. Egor has multiple side projects using neural networks for molecular optimization, NLP, and other areas.