Explaining the reliability of algorithms to humans

Jose Antonio Rodriguez Serrano

Data Processing

Machine learning systems have a problem: they are imperfect and can sometimes err. And we humans have a problem too: we are not yet used to working with imperfect results. In 2018, coinciding with the Football World Cup, a company ventured to forecast the probabilities of each team becoming champion -the original report is not available but you can still …

Text categorization and tag suggestion in a single model

Pau Batlle

Data Processing

In this post, I would like to explain the topic of my work during the 2018 Internship, continuing the research I did in 2017 and explained in another post. The problem we try to solve is the joint classification and tag prediction for short texts. Tag prediction and classification This machine learning problem arises in practical applications such as categorizing …

Agent-based default propagation: adding politics to default propagation in the economy

Jordi Nin and Elena Tomas Herruzo

Data Processing

Default propagation cannot be understood by simply looking at supplier-customer relations as a set of static nodes and edges. The politics of these relations and the information on the current environment play an important role in how a crisis will spread in the economic system. A group of data scientists at BBVA has analyzed that matter in a paper that …

A few Recommendations for a Data Scientist who wants to get started in Recommender Systems

Juan Arévalo

Data Processing

As a Data Scientist, you are expected to be able to build all sort of data products, that may involve simple-yet highly valuable business trends extracted through data querying and cleansing; and sometimes, more sophisticated Machine Learning algorithms for prediction, classification, or even recommendation. However, the cold start in a specific topic may be tough for Data Scientists, especially for …

Bayesian Deep Learning meets Google Cloud for a better forecasting engine at BBVA

Jairo Mejía

Data Processing, News&References

BBVA Data & Analytics have just published a white paper in partnership with Google Cloud that showcases an end-to-end solution to deploy to production a Deep Learning model for time series forecasting. The model incorporates uncertainty of the predictions, which, we believe will have a powerful impact on improving the customer experience of products such as BBVA’s expected expense tracker …

Self-Service Performance Tuning for Hive

Angel Puerto

Data Processing

Hive is a very powerful data warehouse framework based on Apache Hadoop. The two together provide stable storing and processing capabilities for big data analysis. In this article, we will analyze how to monitor metrics, tune and optimize the workflow in this environment with Dr. Elephant. Hive is designed to enable easy data summarization, ad-hoc queries, and big data analysis. …

Improving Predictions in Deep Learning by Modelling Uncertainty

Axel Brando

Data Processing

At BBVA we have been working for some time to leverage transactional data of our clients and Deep Learning modes to offer a personalized and meaningful digital banking experience. Our ability to foresee recurrent income and expenses in an account is unique in the sector. This kind of forecasting helps customers plan budgets, act upon a financial event, or avoid overdrafts. All …

No Problem Too Big; No Solution Too (Computationally) Small

Jairo Mejía

Data Processing

At BBVA Data & Analytics we are constantly tackling business problems with applied maths, statistics or econometrics. There is no problem too big; but it turns out the solution can be sometimes too big. That premise took BBVA’s data scientist Jordi Nin and Jordi Aranda to explore a way to improve the quality of the insights offered by Commerce 360, …

A “weird” Introduction to Deep Learning

Favio Vázquez

Data Processing

There are amazing introductions, courses and blog posts on Deep Learning. I will name some of them in the resources sections, but this is a different kind of introduction: a weird introduction. But why weird? Maybe because it won’t follow the “normal” structure of a Deep Learning post, where you start with the math, then go into the papers, the …