Big Data, Machine Learning & Recommender Systems

Products & Services

"Insanity: doing the same thing over and over again and expecting different results" - Albert Einstein

Information Extraction

Automatic extraction of unstructured data from websites, collections of files, or other data sources.

Predictive Analysis

Predictive models learned from data that allow to estimate future events.

Machine Learning

Machine learning, optimization methods, bioinspired algorithms and evolutionary models.

Recommendation

Collaborative, demographic, content-based or rule-based recommender systems.

Data Clustering

Automatic data clustering of items (users, products, news…) with common relations.

Trends & Dependencies

Automatic detection of trends and dependencies in data from enterprise, media and social networks.

Related Information

Determination of products, news or services similar to each given in real time.

Dashboards

Interactive visual elements that show data, processes and results from machine learning.

Media & Social Networks

Impact of a particular product, topic, event or campaign on social networks and online media.

Personalization

Personalization of information for each user based on their consumption habits.

Patterns & Sequences

Detection of repetitive, habitual, spatial, temporal, recurrent or recurrent behaviors

Automatic Labelling

Extraction of the most relevant terms in news, emails, messages or other text-based sources.

We have prepared a small example that shows the potential of a Recommendation System using the MovieLens movie database.

About us

Research, Innovation, Engineering

BigTrueData born as the join of a Corporate Group and a team of entrepreneurs and researchers that has grown out of the Universidad Politécnica de Madrid (Technical University of Madrid). The company develops innovative solutions using the knowledge, ingenuity, talent, quality and experience that we have gained.

Our technical staff is made up of entrepreneurs, professors, doctors and PhD students of computer science, mathematics and telecommunications. We bring our research projects into line with the development of innovative and disruptive new business solutions, based on our own algorithms and mathematical methods.

Our main research area is the Artificial Intelligence, centered in the Machine Learning field. We are specialized in the design and implementation of brand new and accurate Recommender Systems.

Research

Our most important publications in the Recommender Systems & Machine Learning fields
Information Sciences
Bobadilla, J., Hernando, A., Ortega, F., & Gutierrez, A. (2013). Recommender systems survey, Knowledge Based Systems, 46, 109-132.
Recommender systems have developed in parallel with the web. They were initially based on demographic, content-based and collaborative filtering. Currently, these systems are incorporating social information. In the future, they will use implicit, local and personal information from the Internet of things. This article provides an overview of recommender systems as well as collaborative filtering methods and algorithms; it also explains their evolution, provides an original classification for these systems, identifies areas of future implementation and develops certain areas selected for past, present or future importance.
Information Sciences
Ortega, F., Hernando, A., Bobadilla, J., & Kang, J.H. (2016). Recommending Items to Group of Users using Matrix Factorization based Collaborative Filtering, Information Sciences, 35, 313-324.
In this paper we explain how to perform group recommendations using Matrix Factorization (MF) based Collaborative Filtering (CF). We propose three original approaches to map the group of users to the latent factor space and compare the proposed methods different scenarios. Our study demonstrates that the performance of group recommender systems varies depending on the size of the group, and MF based CF is the best option for group recommender systems.
Information Sciences
Hernando, A., Bobadilla, J., & Ortega, F. (2016). A non negative matrix factorization for collaborative filtering recommender systems based on a Bayesian probabilistic model, Knowledge-based Systems, 97, 188-202.
In this paper we present a novel technique for predicting the tastes of users in recommender systems based on collaborative filtering. Our technique is based on factorizing the rating matrix into two non negative matrices whose components lie within the range [0, 1] with an understandable probabilistic meaning. Thanks to this decomposition we can accurately predict the ratings of users, find out some groups of users with the same tastes, as well as justify and understand the recommendations our technique provides.

Contact us