Close panel

Close panel

Close panel

Close panel

Innovation

Innovation

In an article published a few months ago in'The New Yorker' the British writer John Lanchester explains that in order to write a novel about London, he had to begin by trying to understand “the world of money.” Although Lanchester isn't shy on culture – he grew up between Calcutta, Brunei, and Hong Kong; and was educated at Oxford – his reading about the economy required something of an effort.

Ricardo Forcano, BBVA’s Global Head of Engineering and Organization, participated in the Association for the Advancement of Management’s (APD in Spanish) session on Agile Organizations, where he presented how BBVA is transforming its organization and work methods. “It’s a constant learning process,” Forcano said, referring to BBVA’s efforts to incorporate  the agile methodology across all of its central areas. As a result, the bank is able to provide its customers new solutions more effectively.

In recent months, BBVA Next Technologies has devoted some effort into researching tools and techniques for interpreting machine learning models. These techniques are very useful to understand the predictions of a model (or make others understand them), to extract business insights from a model that has managed to capture the underlying patterns of customers interest, and to debug models in order to ensure they make the right decisions for the right reasons.

In this article we will explain how we have applied these techniques to avoid deploying flawed models into production that seemed totally correct a priori according to standard validation methods.

Thirty years ago this month the internet came online giving consumers the ability to educate themselves on various products and services long before they ever spoke to an expert. For financial services, it signaled a shift in how bankers worked with customers.