Author Archives: admin

CrowdRec at ACM RecSys 2016

The 2016 ACM Conference on Recommender Systems (https://recsys.acm.org/recsys16/) will be taking place 15-19 September in Boston. We are happy that our events/presentations at RecSys 2016 reflect the contribution that CrowdRec has made to shaping RecSys paradigms (cf. the two Past, Present, Future papers), fusing information sources (cf. the new deep learning work), and recommender system evaluation (cf. RecSys Challenge). Here is a full list of RecSys 2016 events co-organized or papers co-authored by CrowdRec members:

RecSys Challenge Workshop 2016
Date: Thursday, Sept 15, 2016, 09:00-17:30
Location: IBM (2217)
http://2016.recsyschallenge.com
Organizers: Fabian Abel, Daniel Kohlsdorf, Martha Larson, Róbert Pálovics, András Benczúr

Workshop on Deep Learning for Recommender Systems (DLRS 2016)
Date: Thursday, Sept 15, 2016, 09:00-12:30
Location: IBM (Aud B)
http://dlrs-workshop.org
Organizers: Alexandros Karatzoglou, Balázs Hidasi, Domonkos Tikk, Oren Sar-Shalom, Haggai Roitman, Bracha Shapira, Lior Rokach

Workshop includes:
Exploring Deep Space: Learning Personalized Ranking in a Semantic Space
Authors: Jeroen Vuurens, Martha Larson, Arjen de Vries
http://arxiv.org/pdf/1608.00276.pdf

Poster Reception
Date: Saturday, Sept 17, 2016, 18:30-22:00
Location: Walker Memorial

Idomaar: A Framework for Multi-dimensional Benchmarking of Recommender Algorithms
Authors: Mario Scriminaci, Andreas Lommatzsch, Benjamin Kille, Frank Hopfgartner, Martha Larson, Davide Malagoli, Andras Sereny and Till Plumbaum: http://ceur-ws.org/Vol-1688/paper-14.pdf

Explicit Elimination of Similarity Blocking for Session-based Recommendation
Authors: Mattia Brusamento, Roberto Pagano, Martha Larson and Paolo Cremonesi: http://home.deib.polimi.it/pagano/recsys2016PosterPaperSimilarityBlockers.pdf

Topical Semantic Recommendations for Auteur Films
Authors: Christian Rakow, Andreas Lommatzsch, and Till Plumbaum
http://www.dai-labor.de/fileadmin/Files/Publikationen/Buchdatei/RecSys2016__RakowLommatzsch__TopicalSemanticRecommendationsForAuteurFilms.pdf

Paper Session 7: Past, Present & Future
Date: Sunday, Sept 18, 2016, 11:20-12:20
https://recsys.acm.org/recsys16/session-7/

Algorithms Aside: Recommendation As The Lens Of Life (Past, present, future paper)
Authors: Tamas Motajcsek, Jean-Yves Le Moine, Martha Larson, Daniel Kohlsdorf, Andreas Lommatzsch, Domonkos Tikk, Omar Alonso, Paolo Cremonesi, Andrew Demetriou, Kristaps Dobrajs, Franca Garzotto, Ayse Göker, Frank Hopfgartner, Davide Malagoli, Thuy Ngoc Nguyen, Jasminko Novak, Francesco Ricci, Mario Scriminaci, Marko Tkalcic, Anna Zacchi

Paper Session 8: Deep Learning
Date: Sunday, Sept 18, 2016, 11:20-12:20
Location: Stratton Student Center (Sala 202)
https://recsys.acm.org/recsys16/session-8/

Parallel Recurrent Neural Network Architectures for Feature-rich Session-based Recommendations
Authors: Balázs Hidasi, Massimo Quadrana, Alexandros Karatzoglou, Domonkos Tikk
http://www.hidasi.eu/content/p_rnn_recsys16.pdf

Paper Session 9: Contextual Challenges
Date: Sunday, Sept 18, 2016, 14:00-15:40
Location: Kresge Auditorium

The Contextual Turn: from Context-Aware to Context-Driven Recommender Systems (Past, present, future paper)
Authors: Roberto Pagano, Paolo Cremonesi, Martha Larson, Balazs Hidasi, Domonkos Tikk, Alexandros Karatzoglou, and Massimo Quadrana
http://home.deib.polimi.it/pagano/portfolio/papers/TheContextualTurn.pdf

Paper Session 11: Algorithms II
Date: Monday, Sept 19, 2016, 10:40-12:20
Location: Kresge Auditorium

Personalized Ranking with Multi-Channel User Feedback (short paper)
Authors: Babak Loni, Roberto Pagano, Martha Larson, Alan Hanjalic

NewsReel at the Algorithms & Data Challenges Meetup

CrowdRec presented the CLEF Newsreel Challenge at the Algorithms with Friends II Meetup in Berlin with around 100 participants.

Andreas Lommatzsch (of TU Berlin) talked about the challenges and findings of the third year of NewsReel, which focused on offline vs online evaluation and stream recommendations. They received very positive feedback from the crowd and are now encouraged to actively plan the 4th incarnation of the challenge.

You can find the slides here – NewsReel_Meetup.pdf

Third International Workshop on Gamification for Information Retrieval (GamifIR 2016)

GamifIR 2016 will be held in conjunction with SIGIR 2016, in Pisa, Italy, on the 21st of July 2016

Goals:

 Many research challenges in the field of IR rely on tedious manual labour. Canonical examples include the manual feedback required to assess the relevance of documents to a given search task or the evaluation of interactive IR approaches. Performing these tasks through Crowdsourcing techniques can be useful, but often fail when motivated users are required to perform a task for reasons other than just being paid per click. A promising approach to increase user motivation is by employing Gamification methods which has been applied in various environments and for different purposes, such as marketing, education, pervasive health care, enterprise workplaces, e-commerce, human resource management and many more.

The Third International Workshop on Gamification for Information Retrieval (GamifIR 2016) focuses on the challenges and opportunities that Gamification can present for the IR community. The workshop, organized in conjunction with SIGIR 2016, aims to bring together researchers and practitioners from a wide range of areas including game design, information retrieval, human-computer interaction, computer games, and natural language processing.

  Continue reading

2nd Budapest RecSys & Personalization Meetup

A CrowdRec, Gravity and MTA STZAKI organized meetup, to take place on the 9th of June in Budapest, Hungary:

Fabian Abel (Data scientist at XING – the primary social network for business contacts in German-speaking countries, Germany; @fabianabel, http://fabianabel.de/) will talk about the some challenges at XING in conjunction with the RecsysChallenge 2016, co-organized by XING and SZTAKI

Title: What’s wrong with you, Recruiter-John? A non-trivial recommender challenge.

Summary: 

Maria from Illusion Inc. recently told her colleague Recruiter-John that she needs an additional team member: “I’m looking for a new team member that can support us in building up our new search engine. Some experience with Lucene or other search technologies and some background in information retrieval would be cool!”. Recruiter-John then did his work and redirected her message to the world: “We are searching for a Data Scientist who has a PhD in Computer Science or some related field, 5 years industry experience in building search engines with Lucene at large scale, is highly skilled in Elixir and Erlang and fits into our young, dynamic team…”. Paul is  currently searching for a job: “I am a Senior Software Engineer with more than 10 years of industry experience in Java, Scala, C++ and 15 other programming languages, familiar with technologies such as Solr, Hadoop, Pig, Hive, Hbase, Cassandra, Riak, … I’m currently looking for a job where I can bring my dog to work.” Bringing together the demand and offer on the job market is a non-trivial problem. In this talk, we will share some of our frustration and will describe how we tackle this problem with recommender systems on XING, a career-oriented social network.  We will give insights on the RecSys challenge (http://recsyschallenge.com) which is our attempt to let the bright minds of the RecSys community solve the recommendation problem that we failed to solve properly over the past four years.

Alexandros Karatzoglou (Researcher at Telefonica, Spain, @alexk_z, http://www.ci.tuwien.ac.at/~alexis/About.html), will talk about how to leverage deep learning technologies for recommender systems.

Title: Deep Learning for Recommender Systems

Summary: Deep Learning (i.e. the return of Neural Networks part deux) is one of the most active and interesting areas in Machine Learning at the moment. New Deep Learning methods have shown to perform in several tasks in Image Processing, Natural Language Processing and Signal Processing. The emergence of these new Machine Learning methods creates new opportunities in the area of Recommender Systems, while at the moment there is relatively little work in the intersection of Deep Learning and Recommender Systems I will try to give an overview of the existing work, and also try to make some educated guesses about the future of Recommender Systems in light of the advancements in Deep Learning.

Guy Rapoport (Software Engineer at Dato, US) will talk about Graphlab Create and its recommendation capabilities.

Title: Practical Recommender Systems Tips

Summary: GraphLab Create is a Python library for scalable Machine Learning. In this talk we will explore different types of recommendation models, and describe how to use them in practice. Guy will talk about his experience in bringing personalization into existing businesses in many different verticals. This lecture will include practical tips and live examples.

Dato & GraphLab Training before the meetup

Please register here:

http://www.meetup.com/Budapest-GraphLab-Users/events/231066711/

2nd Budapest RecSys & Personalization Meetup

Gravity co-organises the 2nd Budapest RecSys & Personalization Meetup, where on the 9th of June, 2016:

 

Fabian Abel (Data scientist at XING – the primary social network for business contacts in German-speaking countries, Germany; @fabianabel, http://fabianabel.de/) will talk about the some challenges at XING in conjunction with the RecsysChallenge 2016, co-organized by XING and SZTAKI

  • Title: What’s wrong with you, Recruiter-John? A non-trivial recommender challenge.

 

Alexandros Karatzoglou (Researcher at Telefonica, Spain, @alexk_z, http://www.ci.tuwien.ac.at/~alexis/About.html), will talk about how to leverage deep learning technologies for recommender systems.

  • Title: Deep Learning for Recommender Systems

 

Guy Rapoport (Software Engineer at Dato, US) will talk about Graphlab Create and its recommendation capabilities.

  • Title: Practical Recommender Systems Tips

 

Get on with it! Recommender system industry challenges move towards real-world, online evaluation

Recommender systems have enormous commercial importance in connecting people with content, information, and services. Historically, the recommender systems community has benefitted from industry-academic collaborations and the ability of industry challenges to drive forward the state of the art. However, today’s challenges look very different from the NetFlix Prize in 2009. This talk features speakers representing two ongoing recommendation challenges that typify the direction in which such challenges are rapidly evolving. The first is the ACM RecSys Challenge (http://2016.recsyschallenge.com), which addresses the task of recommending job openings. Behind this challenge is XING, the social network for business contacts that serves 10 million users in the German-speaking market. The second is CLEF NewsREEL (http://www.clef-newsreel.org/), which addresses the task of recommending news items in online portals. Behind this challenge is plista, specialists in data-driven native advertising and content distribution. Taken together these examples represent the movement of recommender system industry towards offering challenges involving real-world, online evaluation. Success in such challenges requires algorithm s capable of integrating the multiple sources of information available in real-world scenarios. Further, the algorithms must be effective from the perspective of user satisfaction, but also be able to meet technical constraints (i.e., response time, system availability) and business requirements (i.e., item coverage).

  Continue reading

“Think-Forward Tank” on the Future of Recommender Systems

This ‘by-invite-only’ CrowdRec event will take place during the European Conference for Information Retrieval (ECIR) 2016 in Padova (Italy) on March 22, 12:30pm to 17:00pm CET.

The purpose of the “Think-Forward Tank” is to explore what the future (over the next 5 to 10 years, and beyond) holds for the Recommender Systems (RecSys) community, and to recognise forthcoming challenges, domains and possibilities for recommender systems in the future. The doors are wide open, but possible examples are information retrieval, data analytics, and predictive search. Our goal is to push beyond conventional topics and to share our vision with the RecSys community, in an effort to move forward the state of the art.

The output of the event will be a co-authored description of the areas of application in which recsys will be productively employed in the future, both in the service of industry and of society. The description will help to identify the most important research priorities, making it possible for collaboration of industry and academic researchers to focus their efforts in allowing recsys to realize its full future potential. We will target the submission at ACM RecSys 2016 https://recsys.acm.org/recsys16/call/ as a “Past, Present, Future” paper.

If you’d like to take part in the workshop, please contact us at info@crowdrec.eu!

RecSys Challenge 2016 gets underway!

The RecSys Challenge 2016 is co-organized by XING and CrowdRec. RecSys researchers can sign up to participate at: http://2016.recsyschallenge.com

The challenge requires participants to develop algorithm for job recommendation. Given a XING user, the goal is to predict those job postings that a user will click on. The challenge encourages the development of algorithms that are capable of exploiting different sources of information. Participants submit a paper on their solution to the RecSys Challenge Workshop at ACM RecSys 2016.

5th RecSysNL meetup

The 5th RecSysNL meetup was held on November 24th in Elsevier, Amsterdam. It was a successful meetup and attracted many people from both academia and industry from all over the Netherlands.

Rolf Drög and Mikel Porras Hoogland gave an overview of their social music platform called Kollekt.fm. They talked about a music recommender systems they are developing together with TU Delft for Kollekt.fm within the CrowdRec project.

Continue reading

6th RecSysNL meetup

The 6th RecSysNL meetup will be held on September 28, 2016 starting at 17:30. It will be hosted by ORTEC in Amsterdam, at Condensatorweg 54, 1014 AX Amsterdam.

The RecSysNL Meetup is a meetup for people who are interested in recommender systems, user behavior analytics, machine learning, Artificial Intelligence and all related topics.

 

Continue reading