Applying Transfer Learning to Natural Language models

Maria Hernandez Data Processing

Natural Language Processing (NLP) has been one of the key fields of Artificial Intelligence since its inception. After all, language is one of the things that defines human intelligence. In recent years, NLP has undergone a new revolution similar to the one that took place 20 years ago with the introduction of statistical and Machine Learning techniques. This revolution is …

Uncertainty Models and Detection of Balance Anomalies

Jose Antonio Rodriguez Serrano Data Processing

The development of Artificial Intelligence in the financial sector drives the creation of new data-based products, which are often linked to a new form of relationship between customers and financial institutions. In this sense, one of the main trends is related to the generation of personalized services and products that allow us to better manage our finances. The BBVA app …

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 …

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

E052179 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 …

It is Not About Deep Learning, But Learning How to Represent

Beatriz Alonso Data Processing

Recently, we setup a workgroup dedicated to Deep Learning (DL). Workgroups offer opportunities to share internally ideas, concepts, resources, code, etc. Additionally, they are meant to promote the use of Machine Learning at BBVA. I remember vividly how José Antonio Rodríguez, one of the impellers of this workgroup, told us back then: “We should call it the workgroup on representation …

A Cost-Effective and Scalable Collaborative Filtering based Recommender System

Ivan Fernández Data Processing

Last 26th of September we had the opportunity to present a collaboration between BBVA Data & Analytics and BEEVA at the Theatre of Partners during the AWS Summit Madrid 2017. In the conference, we presented a cost-effective approach for collaborative filtering based Recommender Systems (RS), that scales to millions of users and a million products. Our implementation made use of …

Cleansing and Exploratory Data Analysis with Apache Spark and Optimus

Favio Andre Vazquez Prieto Data Processing

Outdated, inaccurate, or duplicated data won’t drive optimal data driven solutions. When data is inaccurate, leads are harder to track and nurture, and insights may be flawed. The data on which you base your big data strategy must be accurate, up-to-date, as complete as possible, and should not contain duplicate entries. Clean data results in better decisions. Cleaning data is …

There is no Such Thing as a Certain Prediction

Leonardo Baldassini Data Processing

One question that naturally springs up when imagining what Artificial Intelligence (AI) can bring to the banking industry, and one that we get asked fairly often, is: Can you predict people’s expenses? As it is often the case, such a simple question is in fact only apparently simple. The prediction of personal financial transactions may range from estimating the amount …

What Does Wind Look Like?

Jordi Aranda Data Processing

In our recent collaboration with United Nations Global Pulse to measure the economic impact of natural disasters we analyzed purchase behaviors when Hurricane Odile struck Baja California Sur in September 2014. As part of the study we visualized the strength of the winds and showed how the hurricane initially formed until finally making landfall. In this article I describe how we …

Recommender systems: Marketing gets personal

Jerry Finn Data Processing

Did you ever get the feeling that Amazon understands your desires better than your spouse? Did you ever search for a vacation in Galicia on Google and then notice you see more ads trying to sell you sea food and raincoats? This is thanks to recommender systems brought to you by the phenomenon of Big Data. In today’s world, businesses …

Reference Generation: A Method for Venue Recommendation

Jerry Finn Data Processing

Being concise is often a virtue and sometimes it is also a necessity. It’s especially interesting to explain something as complex as data science in just 6 minutes. This was the idea behind the Pecha-Kucha talks at the NetSci2015 conference of the Network Science Society in Zaragoza, Spain. The Pecha-Kucha presentation style recommends 20 slides for 20 seconds each, forcing …

Predicting Regional Economic Indices

Jerry Finn Data Processing

It’s not unusual for people to complain about the timeliness of macroeconomic statistics. Governments are constantly revising GDP figures and unemployment rates well after the fact. It seems when it comes to economic statistics it’s tough to make predictions about the past. Other limitations are that the nature of the data that is used as input to official government economic …