Marc Torrens - Academia.edu (original) (raw)
Papers by Marc Torrens
International Computer Music Conference, 2005
Conference on Recommender Systems, Sep 26, 2010
We welcome you to the 4th ACM Recommender Systems Conference (ACM RecSys 2010), this time from be... more We welcome you to the 4th ACM Recommender Systems Conference (ACM RecSys 2010), this time from beautiful and sunny Barcelona. After three fantastic preceding conferences, we took on the challenge of continuing on the success trend knowing that a city such as Barcelona would offer the ideal setting. Not only is Barcelona a top tourism destination but it has also a very bustling industry that includes large companies and young startups in recommender systems and related areas. RecSys is maturing as a research area and you will find several signs of that maturity reflected in these proceedings. One sign is becoming cumulative: performance of new algorithms is compared to previous algorithms and contrasts are made between performance on different datasets. With maturity, however, also comes a questioning of assumptions. For example, you will find papers that argue for different measures of success than prediction accuracy, such as stability and coverage. Despite maturity, the field also continues to be creative. You will find papers exploring new ways of collecting user preferences beyond like/dislike of individual items, such as pairwise orderings or allocation of points among a set of items. You will also find research identifying and exploiting the specific characteristics of non-standard item types to recommend, ranging from people to groups to recipes to research papers. For the first time, ACM RecSys 2010 had more than 200 submissions. Of 129 full paper submissions, 25 were accepted (19.4%) for oral presentation at the conference. Of 78 short paper submissions, 32 were accepted (41.0%) for poster presentation. In addition, we introduced a new track for submission of demos and case study reports, which will also be presented at the poster session. The program also includes three invited tutorials, by senior researchers Joe Konstan, Ricardo Baeza-Yates, and Guy Shani, and an invited keynote by Edouard Servan-Schreiber. The conference begins with an industry panel examining the future of recommender systems in several different industries, and how it relates to search. Panelists from Neo Metrics Barcelona, Bloomberg.com, YouTube, SAP, and Avail Intelligence will join industry chairs Ido Guy and Alex Jaimes on stage. Tuesday morning begins with a panel on contests and challenges. In addition to a skeptic's voice questioning the wisdom of contests overall, the panel will explore alternative tasks for contests besides prediction and ranking, such as making creative use of the outputs of a fixed recommender engine, or eliciting inputs for a recommender engine. In addition to the main program, we would also like to highlight the growing success of the collocated workshops. This year we have seven workshops distributed on two different days of the conference. These workshops include most of the new trending research lines in recommender systems. They focus on application areas of RecSys such as music, e-Learning, or the social web. Others analyze some cross-cutting concerns in research such as how to deal with contextual or heterogeneous information, or how to bring the user into the loop in the evaluation phase. Finally, one workshop specifically focuses on the practical concerns of deploying and evaluating recommender systems in real-world settings.
Harvard Deusto business review, 2019
?Que deben hacer los bancos tradicio-nales para lograr un modelo sosteni-ble que les permita sobr... more ?Que deben hacer los bancos tradicio-nales para lograr un modelo sosteni-ble que les permita sobrevivir en un contexto marcado por la presencia ca-da vez mas inmersiva de las tecnolo-gias digitales, las criptomonedas, la inteligencia artificial y las nuevas re-gulaciones? ?Como pueden competir con las empresas fintech y los gigantes de Internet? La solucion pasa por ex-plotar uno de sus activos de mayor va-lor, los datos transaccionales de los clientes (sus autenticos habitos de consumo), aprovechandolos como ventaja competitiva, y por apostar por el rol de la banca como plataforma o como ecosistema, integrando actores mas alla de los de su sector.
National Conference on Artificial Intelligence, 1999
Many information systems are used in a problem solving context. Examples are travel planning syst... more Many information systems are used in a problem solving context. Examples are travel planning systems, catalogs in electronic commerce, or agenda planning systems. They can be made more useful by integrating problem-solving capabilities into the information systems. This poses the challenge of scaleability: when hundreds of users access a server at the same time, it is important to avoid excessive computational load. We present the concept of smart clients: lightweight problem-solving agents based on constraint satisfaction which can carry out the computation-and communication-intensive tasks on the user's computer. We present an example of an air travel planning system based on this technology.
La presente invention concerne des systemes et des procedes utilises pour produire des elements d... more La presente invention concerne des systemes et des procedes utilises pour produire des elements de medias composites a partir d'elements de medias comprenant chacun des articles de medias associes a une pluralite d'utilisateurs. Certains modes de realisation concernent des recommandations individuelles et/ou de groupe pour creer une liste de diffusion de groupe par regroupement de donnees de preference d'utilisateur concernant une pluralite d'utilisateurs dans un groupe. D'autres modes de realisation concernent des systemes et des procedes qui permettent a des utilisateurs dans un groupe de partager et de diffuser une liste de diffusion de groupe, chacun des utilisateurs possedant un dispositif de diffusion de medias. D'autres modes de realisation concernent des systemes et des procedes utilises pour etablir de maniere dynamique une liste de diffusion composite qui peut etre mise a jour lorsque des utilisateurs integrent le groupe et/ou quittent le groupe. Ce...
Dans un systeme de communaute de mode en ligne (100), des utilisateurs fournissent un contenu d&#... more Dans un systeme de communaute de mode en ligne (100), des utilisateurs fournissent un contenu d'images personnelles, tel que des images de mode utilisateur numeriques (104, 700) qui comprennent les utilisateurs eux-memes portant plusieurs articles de mode ensemble, sur la base d'une interaction communautaire. Les utilisateurs fournissent egalement des informations concernant les articles de mode, y compris des informations de liaison (108) a un fournisseur de chaque article de mode ainsi que des donnees de mode (106), telles que la marque, la couleur, le style, etc. Un systeme d'interface utilisateur (116) permet aux utilisateurs de rechercher, d'acceder et d'interagir a propos des ensembles de modes utilisateurs.
MusicStrandsTMhas launched a platform devoted to the discovery and exploration of music for the e... more MusicStrandsTMhas launched a platform devoted to the discovery and exploration of music for the end-user. The services are freely accessible through our web site www. MusicStrands.com. The goal of this demonstration paper is to describe the main services offered by our proprietary technology which is based on Artificial Intelligence techniques to encode and predict musical users tastes. Our technology allows users to better enjoy music by facilitating the process of discovering and exploring new music.
Colloids and Surfaces A: Physicochemical and Engineering Aspects, 2011
AI for Good (Inteligencia Artificial para el Bien) es una plataforma de las Naciones Unidas con e... more AI for Good (Inteligencia Artificial para el Bien) es una plataforma de las Naciones Unidas con el objetivo de estudiar e impulsar objetivos de desarrollo sostenible a través de la Inteligencia Artificial (IA). En este capítulo, analizamos algunas de las aplicaciones de la IA y su potencial en esos objetivos de desarrollo sostenible. En concreto, estudiamos como la digitalización y la Inteligencia Artificial pueden ayudar de una forma disruptiva a dos de los objetivos de desarrollo sostenible propuestos por las Naciones Unidas: 1) la mejor organización de las ciudades, y 2) la gestión óptima del agua.Objectius de Desenvolupament Sostenible::6 - Aigua Neta i SanejamentObjectius de Desenvolupament Sostenible::11 - Ciutats i Comunitats SosteniblesPostprint (published version
This document gives the specification of version 2.01 of the Constraint Choice Language (CCL). CC... more This document gives the specification of version 2.01 of the Constraint Choice Language (CCL). CCL is designed as a language to be used for agent communication which directly supports the expression of choice and choice problems in the content of agent messages. This version of CCL has been adopted by FIPA as a standard FIPA-compliant content language named FIPA-CCL.
Frontiers in Artificial Intelligence and Applications
Prioritization of activities is one of the many facets in digital products management. In this st... more Prioritization of activities is one of the many facets in digital products management. In this study, we propose an alternative point of view on Portofolio Projects Management, in order better understand their relationship between performance and importance and how resources can be allocated taking into account these two categories. An application of the presented methodology to a real use case in the Digital Department of SEAT S.A. is discussed to show current results and future developments.
Harvard Deusto business review, 2020
Many information systems are used in a problem solving context. Examples are travel planning syst... more Many information systems are used in a problem solving context. Examples are travel planning systems, catalogs in electronic commerce, or agenda planning systems. They can be made more useful by integrating problem-solving capabilities into the information systems. This poses the challenge of scalability: when hundreds of users access a server at the same time, it is important to avoid excessive computational load. In this paper, we present an approach, called reality, that allows to significantly extend the reach of electronic commerce in travel. Our application addresses in particular the challenge of modeling customers ’ personal preferences and providing solutions that are tailored to just those preferences. In contrast to existing technology, which allow to optimize only a small and predefined set of preferences, our tool allows a wide variety that can accurately model the preferences of different customers.
Entropy, 2022
Payment data is one of the most valuable assets that retail banks can leverage as the major compe... more Payment data is one of the most valuable assets that retail banks can leverage as the major competitive advantage with respect to new entrants such as Fintech companies or giant internet companies. In marketing, the value behind data relates to the power of encoding customer preferences: the better you know your customer, the better your marketing strategy. In this paper, we present a B2B2C lead generation application based on payment transaction data within the online banking system. In this approach, the bank is an intermediary between its private customers and merchants. The bank uses its competence in Machine Learning driven marketing to build a lead generation application that helps merchants run data driven campaigns through the banking channels to reach retail customers. The bank’s retail customers trade the utility hidden in its payment transaction data for special offers and discounts offered by merchants. During the entire process banks protects the privacy of the retail c...
The Financial Technology Handbook for Investors, Entrepreneurs and Visionaries, 2016
Proceedings of the 2003 ACM symposium on Applied computing - SAC '03, 2003
International Computer Music Conference, 2005
Conference on Recommender Systems, Sep 26, 2010
We welcome you to the 4th ACM Recommender Systems Conference (ACM RecSys 2010), this time from be... more We welcome you to the 4th ACM Recommender Systems Conference (ACM RecSys 2010), this time from beautiful and sunny Barcelona. After three fantastic preceding conferences, we took on the challenge of continuing on the success trend knowing that a city such as Barcelona would offer the ideal setting. Not only is Barcelona a top tourism destination but it has also a very bustling industry that includes large companies and young startups in recommender systems and related areas. RecSys is maturing as a research area and you will find several signs of that maturity reflected in these proceedings. One sign is becoming cumulative: performance of new algorithms is compared to previous algorithms and contrasts are made between performance on different datasets. With maturity, however, also comes a questioning of assumptions. For example, you will find papers that argue for different measures of success than prediction accuracy, such as stability and coverage. Despite maturity, the field also continues to be creative. You will find papers exploring new ways of collecting user preferences beyond like/dislike of individual items, such as pairwise orderings or allocation of points among a set of items. You will also find research identifying and exploiting the specific characteristics of non-standard item types to recommend, ranging from people to groups to recipes to research papers. For the first time, ACM RecSys 2010 had more than 200 submissions. Of 129 full paper submissions, 25 were accepted (19.4%) for oral presentation at the conference. Of 78 short paper submissions, 32 were accepted (41.0%) for poster presentation. In addition, we introduced a new track for submission of demos and case study reports, which will also be presented at the poster session. The program also includes three invited tutorials, by senior researchers Joe Konstan, Ricardo Baeza-Yates, and Guy Shani, and an invited keynote by Edouard Servan-Schreiber. The conference begins with an industry panel examining the future of recommender systems in several different industries, and how it relates to search. Panelists from Neo Metrics Barcelona, Bloomberg.com, YouTube, SAP, and Avail Intelligence will join industry chairs Ido Guy and Alex Jaimes on stage. Tuesday morning begins with a panel on contests and challenges. In addition to a skeptic's voice questioning the wisdom of contests overall, the panel will explore alternative tasks for contests besides prediction and ranking, such as making creative use of the outputs of a fixed recommender engine, or eliciting inputs for a recommender engine. In addition to the main program, we would also like to highlight the growing success of the collocated workshops. This year we have seven workshops distributed on two different days of the conference. These workshops include most of the new trending research lines in recommender systems. They focus on application areas of RecSys such as music, e-Learning, or the social web. Others analyze some cross-cutting concerns in research such as how to deal with contextual or heterogeneous information, or how to bring the user into the loop in the evaluation phase. Finally, one workshop specifically focuses on the practical concerns of deploying and evaluating recommender systems in real-world settings.
Harvard Deusto business review, 2019
?Que deben hacer los bancos tradicio-nales para lograr un modelo sosteni-ble que les permita sobr... more ?Que deben hacer los bancos tradicio-nales para lograr un modelo sosteni-ble que les permita sobrevivir en un contexto marcado por la presencia ca-da vez mas inmersiva de las tecnolo-gias digitales, las criptomonedas, la inteligencia artificial y las nuevas re-gulaciones? ?Como pueden competir con las empresas fintech y los gigantes de Internet? La solucion pasa por ex-plotar uno de sus activos de mayor va-lor, los datos transaccionales de los clientes (sus autenticos habitos de consumo), aprovechandolos como ventaja competitiva, y por apostar por el rol de la banca como plataforma o como ecosistema, integrando actores mas alla de los de su sector.
National Conference on Artificial Intelligence, 1999
Many information systems are used in a problem solving context. Examples are travel planning syst... more Many information systems are used in a problem solving context. Examples are travel planning systems, catalogs in electronic commerce, or agenda planning systems. They can be made more useful by integrating problem-solving capabilities into the information systems. This poses the challenge of scaleability: when hundreds of users access a server at the same time, it is important to avoid excessive computational load. We present the concept of smart clients: lightweight problem-solving agents based on constraint satisfaction which can carry out the computation-and communication-intensive tasks on the user's computer. We present an example of an air travel planning system based on this technology.
La presente invention concerne des systemes et des procedes utilises pour produire des elements d... more La presente invention concerne des systemes et des procedes utilises pour produire des elements de medias composites a partir d'elements de medias comprenant chacun des articles de medias associes a une pluralite d'utilisateurs. Certains modes de realisation concernent des recommandations individuelles et/ou de groupe pour creer une liste de diffusion de groupe par regroupement de donnees de preference d'utilisateur concernant une pluralite d'utilisateurs dans un groupe. D'autres modes de realisation concernent des systemes et des procedes qui permettent a des utilisateurs dans un groupe de partager et de diffuser une liste de diffusion de groupe, chacun des utilisateurs possedant un dispositif de diffusion de medias. D'autres modes de realisation concernent des systemes et des procedes utilises pour etablir de maniere dynamique une liste de diffusion composite qui peut etre mise a jour lorsque des utilisateurs integrent le groupe et/ou quittent le groupe. Ce...
Dans un systeme de communaute de mode en ligne (100), des utilisateurs fournissent un contenu d&#... more Dans un systeme de communaute de mode en ligne (100), des utilisateurs fournissent un contenu d'images personnelles, tel que des images de mode utilisateur numeriques (104, 700) qui comprennent les utilisateurs eux-memes portant plusieurs articles de mode ensemble, sur la base d'une interaction communautaire. Les utilisateurs fournissent egalement des informations concernant les articles de mode, y compris des informations de liaison (108) a un fournisseur de chaque article de mode ainsi que des donnees de mode (106), telles que la marque, la couleur, le style, etc. Un systeme d'interface utilisateur (116) permet aux utilisateurs de rechercher, d'acceder et d'interagir a propos des ensembles de modes utilisateurs.
MusicStrandsTMhas launched a platform devoted to the discovery and exploration of music for the e... more MusicStrandsTMhas launched a platform devoted to the discovery and exploration of music for the end-user. The services are freely accessible through our web site www. MusicStrands.com. The goal of this demonstration paper is to describe the main services offered by our proprietary technology which is based on Artificial Intelligence techniques to encode and predict musical users tastes. Our technology allows users to better enjoy music by facilitating the process of discovering and exploring new music.
Colloids and Surfaces A: Physicochemical and Engineering Aspects, 2011
AI for Good (Inteligencia Artificial para el Bien) es una plataforma de las Naciones Unidas con e... more AI for Good (Inteligencia Artificial para el Bien) es una plataforma de las Naciones Unidas con el objetivo de estudiar e impulsar objetivos de desarrollo sostenible a través de la Inteligencia Artificial (IA). En este capítulo, analizamos algunas de las aplicaciones de la IA y su potencial en esos objetivos de desarrollo sostenible. En concreto, estudiamos como la digitalización y la Inteligencia Artificial pueden ayudar de una forma disruptiva a dos de los objetivos de desarrollo sostenible propuestos por las Naciones Unidas: 1) la mejor organización de las ciudades, y 2) la gestión óptima del agua.Objectius de Desenvolupament Sostenible::6 - Aigua Neta i SanejamentObjectius de Desenvolupament Sostenible::11 - Ciutats i Comunitats SosteniblesPostprint (published version
This document gives the specification of version 2.01 of the Constraint Choice Language (CCL). CC... more This document gives the specification of version 2.01 of the Constraint Choice Language (CCL). CCL is designed as a language to be used for agent communication which directly supports the expression of choice and choice problems in the content of agent messages. This version of CCL has been adopted by FIPA as a standard FIPA-compliant content language named FIPA-CCL.
Frontiers in Artificial Intelligence and Applications
Prioritization of activities is one of the many facets in digital products management. In this st... more Prioritization of activities is one of the many facets in digital products management. In this study, we propose an alternative point of view on Portofolio Projects Management, in order better understand their relationship between performance and importance and how resources can be allocated taking into account these two categories. An application of the presented methodology to a real use case in the Digital Department of SEAT S.A. is discussed to show current results and future developments.
Harvard Deusto business review, 2020
Many information systems are used in a problem solving context. Examples are travel planning syst... more Many information systems are used in a problem solving context. Examples are travel planning systems, catalogs in electronic commerce, or agenda planning systems. They can be made more useful by integrating problem-solving capabilities into the information systems. This poses the challenge of scalability: when hundreds of users access a server at the same time, it is important to avoid excessive computational load. In this paper, we present an approach, called reality, that allows to significantly extend the reach of electronic commerce in travel. Our application addresses in particular the challenge of modeling customers ’ personal preferences and providing solutions that are tailored to just those preferences. In contrast to existing technology, which allow to optimize only a small and predefined set of preferences, our tool allows a wide variety that can accurately model the preferences of different customers.
Entropy, 2022
Payment data is one of the most valuable assets that retail banks can leverage as the major compe... more Payment data is one of the most valuable assets that retail banks can leverage as the major competitive advantage with respect to new entrants such as Fintech companies or giant internet companies. In marketing, the value behind data relates to the power of encoding customer preferences: the better you know your customer, the better your marketing strategy. In this paper, we present a B2B2C lead generation application based on payment transaction data within the online banking system. In this approach, the bank is an intermediary between its private customers and merchants. The bank uses its competence in Machine Learning driven marketing to build a lead generation application that helps merchants run data driven campaigns through the banking channels to reach retail customers. The bank’s retail customers trade the utility hidden in its payment transaction data for special offers and discounts offered by merchants. During the entire process banks protects the privacy of the retail c...
The Financial Technology Handbook for Investors, Entrepreneurs and Visionaries, 2016
Proceedings of the 2003 ACM symposium on Applied computing - SAC '03, 2003