The NIPS Chronicles: What We Saw There

Leonardo Baldassini AI Factory was there

It may have become a tradition: December is the time when the ripest fruits of 12 months of global research in machine learning are showcased and the future trends defined and outlined in what seems to have become the most important – or at the very least most hyped – gathering on the subject. Following the escalating success it has …

First, We Look Back. Then We Look Forward

Beatriz Alonso News&References

As 2017 comes to an end, it is the ideal moment to draw up a list of the achievements made during this period and, of course, discuss the new challenges that lie ahead. Our co-CEOs Fabien Girardin and Jon Ander Beracoechea have just closed the review of our yearly objectives highlighting the efforts and their metrics to deliver business impact, …

What we saw at Open Data Science Conference Europe 2017

Rafael Hernández AI Factory was there

ODSC London 2017 showed us an amazing variety of tools, libraries, notebooks and data science apps. There were 75 speakers, plus 1.500 attendees and literally no room for more. It doesn’t mind if you prefer Python, R or even Julia. Whether you’re into data visualization, academic research or open source ML libraries. Over there we found the usual hot topics, …

What we saw at Spark Summit Europe 2017: More Spark Libraries, Real Machine Learning systems into production, and the reality of Deep Learning in Spark

Beatriz Alonso AI Factory was there

A month ago, the latest Spark Summit Europe, the world’s largest event for the Apache Spark™ Community, was held in Dublin with the participation of more than 1200 developers, engineers, data scientist, researchers and business professionals. José A. Rodríguez, one of our data scientists, had the opportunity to participate as a speaker with a talk in which he explained a …

Recommended Readings on Data Science

Juan Murillo News&References

The journey that has taken data and its applications from the periphery to the heart of today’s debate has multiple ramifications: social, ethical and legal questions about the opportunities and risks of “datification” in our society, business aspects around the challenge of transforming data into innovative solutions perceived as a new value by customers, and technical and methodological aspects around …

What we saw at ECML & PKDD 2017

Elena Tomas Herruzo AI Factory was there

Last September I had the pleasure to attend to the European Conference on Machine Learning (ECML), which has been held simultaneously with the Principles and Practice of Knowledge Discovery in Databases Conference (PKDD) for the last 13 years. This year the conference was held in Skopje, where they received us with an excellent and priceless Balkan hospitality. The capital of …

Digital Transformation and Big Data in Companies

Josep Amoros Vision&Values

During the last International Symposium of Applied Innovation IMAT, held from 28 to 30 June in Valencia, our colleague Josep Amorós, responsible for Commerce360, participated as a speaker with a talk dedicated to Digital Transformation and Big Data in companies, and the organization of the event has interviewed him to know his points of view in this field. You can …

Can People Analytics Transform Management?

Antonio Moneo News&References

This article is a brief summary of the contents of the course “People Analytics: Transforming Management with Behavioral Data”, led by Ben Waber and Sandy Pentland at the MIT Media Lab in July 24 and 25, 2017. The content of the article is based on their explanation and bibliographic references. Background People Analytics is a discipline of Social Physics that …

Improving the Response Rate of Non-Customer Campaigns with SMOTE Algorithm

Angel Reyes Obispo CRM&Advice

Background Attracting new customers is a challenge for any company, and the response rate to marketing campaigns is usually low among non-customers. Traditional Machine Learning algorithms, such as Logistic Regression, can classify potential customers and predict the result of marketing campaigns, but their predictive accuracy is limited when the data is imbalanced (Chawla, Bowyer, Hall & Kegelmeyer, 2002). Responses to …

The Transformation of a Bank into a Digital Business

Beatriz Alonso Vision&Values

Last week, The Economist, one of the world’s most respected publications in the economic sphere, has written up an article on BBVA Group, entitled “BBVA, A Spanish Bank, Reinvents itself as a Digital Business”. Throughout the text, describe the initiatives that BBVA, as a global bank, is carrying out to become the bank of the future, and the reasons why …

Personalizing Banking Services with Advanced Data Analytics

Teresa Correas CRM&Advice

In the traditional banking model, data was produced by the customer and processed by data analysts. Customer’s income and expenses were used to understand global trends and design products and services attractive for specific segments. BBVA is leveraging advanced analytics methods and technology to give users full control over their data and help them understand their financial health to make …

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 …

Presentation of Urban Discovery: Our Contribution to an Improved Vision of Big Cities

Beatriz Alonso AI Factory Talks

Last September 21st, at BBVA Innovation Center, we presented the results of our last research on territorial analytics: Urban Discovery, a new tool developed together with CARTO, that shows how the analytics of anonymized credit card data can serve to identify functional areas in Madrid, Barcelona and Mexico City, to describe city main dynamics and areas of specialization, and to …

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 …

What we saw at Spark Summit 2017: Spark embraces Deep Learning

Mauricio Ciprian AI Factory was there

Spark Summit 2017, which took place in San Francisco in June, brought together more than 3,000 data scientists, developers and industry experts that participated in more than 170 to discuss recent developments and future trends that will shape the future of the data industry. This is the biggest worldwide event of the Apache Spark community, the technology that has become …

Rediscovering Cities through Credit Card Data (Part 2)

Juan Murillo Data Stories

— Results interpretation from an urban perspective Project Background In a previous paper we outlined the methodology, models, and tools used for the analytical and graphical representation of the Urban Discovery project that we developed together with CARTO. In this second part, the focus is on the functionality of the results in order to interpret and improve the administration of …

Rediscovering Cities through Credit Card Data (Part 1)

Juan de Dios Romero Data Stories

— Analytical and Technological Process Administrative municipal boundaries, such as districts and neighbourhoods, are currently used not only to rule cities but also to describe the behaviour of their citizens. In fact, official statistics and open data are published using these divisions. However they may not be the best option for none of these purposes; nowadays, people and businesses? expand …

Improving Customer Experience with Forecasting Models

Mauricio Ciprian CRM&Advice

Direct debit and credit cards have made the lives of many easier. They have allowed us to save time and headaches, and helped us finance goods that exceed our monthly purchasing power. Sometimes, they have also created situations when an unforeseen payments came through in an unexpected moment with a low balance the missing payment involves a penalty. To solve …

What we saw at RecSys 2017 Conference

Marco Creatura AI Factory was there

RecSys, which took place in Como last 27th August 2017, is one of the largest academic conferences on Recommender Systems (RecSys) and has reached this year its eleventh edition with an all time record of attendees (627), proving the rising importance of Recommender Systems in the current digital agenda. At BBVA Data & Analytics, we believe that Recommender Systems can …

Learning from Cardiac Arrhythmias to Improve Customer Satisfaction — Working with Imbalanced Data

Felipe Alonso-Atienza CRM&Advice

Background Customer satisfaction is a complex indicator. It can change after every interaction, can be influenced by external factors, and can lead to multiple outcomes. Cumulative dissatisfaction can lead the customer to terminate the relationship with the service provider and yet, it is difficult to measure with traditional methods like customer satisfaction surveys. Machine Learning algorithms offer today the possibility …

Our Reading List about Machine Learning for Designers

Fabien Girardin News&References

At BBVA Data & Analytics, we continuously collaborate with design teams at BBVA to create user experiences that rely on machine learning techniques (e.g. predictive models, recommender systems). We documented that interdisciplinary practice in Experience Design in the Machine Learning Era that then led to a contribution in collaboration with Neal Lathia from Skyscanner at the AAAI 2017 Spring Symposia …

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 …

BBVA Data & Analytics Awarded by The Banker Technology Projects of the Year Award

Fco. Javier López Peñalver News&References

Interview with Francisco Javier López Peñalver and Jordi Nin   Jordi Nin — Data Scientist at BBVA Data & Analytics Jordi holds a Ph.D. in Computer Science, with over 75 research publications in journals, conferences and book chapters. He was granted with the Outstanding Ph.D. Award of the UAB computer science department. Jordi’s thesis was devoted to use several machine …

Understanding economic redistribution with credit card payments

Jose Javier Ramasco Data Stories

Background Cities contain neighborhoods that perform economically better than others. But in some cases the differences are extreme, as it happens in Rio the Janeiro where the average income of rich neighborhoods like Copacabana and Ipanema can be up to 100% higher than in the favelas, as stated by the United Nations. Inequality is a common issue for many cities …

Big Data: “Volume is not the problem but the generation of value in an environment with such diversity”

Jon Ander Beracoechea Vision&Values

Jon Ander Beracoechea — Co-CEO at BBVA Data & Analytics Jon holds a Ph.D. in Electrical Engineering and has published multiple papers in the field of adaptive signal processing. He has been applying advanced analytics and machine learning techniques in the banking industry for 9 years in áreas such as CCAR stress testing (Moody’s) or derivatives pricing (Banco Santander). This …

7 Challenges for the Global Digital Economy

Antonio Moneo Vision&Values

The digital global economy will continue to expand and diversify in 2017. New technologies, customer with new habits and global threats will open opportunities and threats for businesses in different sectors. This article summarizes some of them. New technologies In the next couple of years, Blockchain technologies will consolidate and be applied to different and innovative uses increasing transparency and …

Reinforcement Learning for Pricing Strategy Optimization

Elena Krasheninnikova Risk scoring & Pricing

Flipping a pancake is a complex move that humans need to learn through experimentation and repetition. So, how could a robot learn to flip a pancake? Let’s imagine that there is an robotized armed capable of performing the same moves as a human arm. The hand is holding a frying pan, and the dough is cooked and has the shape …

Creating Value from Geolocated Financial Data

Beatriz Alonso News&References

Recently, took place Carto Locations 2017, an immersive 2-day summit on the latest industry developments, innovation and insights in the world of location intelligence. Along with other leading business professionals and industry experts Elena Alfaro gave an overview of our activities in the fields of analytics, data visualization, geospatial analysis, and data science participated. She particularly explained how we are …

How to Improve Customer Service Using Text Analytics?

César de Pablo Sánchez CRM&Advice

This article is a brief summary of three presentations given at the monthly Data Meetup organized by BBVA Data & Analytics. What happens when a comment is sent through a BBVA website, mobile application or email? Every day, BBVA receives thousands of emails from customers who want to ask questions or express their opinions about the quality of the services …

Urban Analytics to Measure the Economic Impact of Traffic Calming

Juan Murillo Data Stories

Cities are physical hardware that withstand overlapped dynamics, resulting into very complex systems. Any change in one of its boundary conditions produces positive and negative effects. Traditionally, urbanists have tried to measure those effects -mainly through surveys- in order to get information whether the management decisions were producing the desired results. Digitization has brought two major innovations for city managers: …