Internship
User Modeling in an Adaptive Recommender System
Cédric Archambeau
Guillaume Bouchard
Gregorio Convertino
The Machine Learning for Services (MLS) team is opening an internship position for a research assistant in the domain of machine learning and user modeling for an idea management system (IMS).
Idea management systems (see www.jpb.com/creative/ideaManagementIntro.pdf for an introduction) are a class of web2.0 tools for the enterprise to help organisations or local communities better manage the idea generation process and make informed decisions. The goal of the system is to share ideas, collaboratively judge them and select the most promising ones as part of a grassroots deliberation process.
The team is building novel software to gather feedback from user communities. The focus is on web-based IMS that support either collaborative innovation within an enterprise (extending tools such as IdeaScale, Spigit) or large-scale deliberation within civic communities (extending current political debate forums such as www.uspoliticsonline.com or www.newsring.com). In the context of these applications, we are interested in studying and inventing tools that seamlessly integrate human input with machine intelligence (also called mixed-initiative tools).
The successful candidate must have both the skills and interest to:
- Implement machine learning algorithms for collaborative filtering and recommendation. In particular, online, adaptive and large-scale approaches will be considered. Recommender systems have been popularised by the Netflix challenge, where the goal was to recommend movies to users based on the observed ratings of previously viewed movies. This data imputation problem can be formalised as a matrix factorisation problem where most of the entries are missing.
- Integrate the input of machine learning algorithms, crowd-sourcing, and expert human operators in order to power the idea management functions: e.g., a recommender engine (with learning) integrated with a user-friendly dashboard to efficiently categorize, relate, and score ideas, map ideas onto reviewers, etc.
- Run systematic user experiments on the prototypes in the lab or with crowds (http://crowdflower.com/), analyze user data to model the user behavior (performance, error rate, learning), and through simulations test these models on larger datasets.
Applicants should have experience in prototyping, developing, and testing machine learning and computational statistics solutions, e.g., for knowledge representation, content categorization, and recommendation systems. They will have to demonstrate their capacity to define and/or implement research plans, to carry out leading research through collaboration withXerox researchers and the wider academic community.
Requirements:
BS or MS in Computer Science or a related field with expertise in the area(s) of machine learning and computational linguistics. He or she will have work experience with developing machine learning algorithms in his/her preferred language (such as Python/Numpy or Matlab) and using statistical tools such as R or SAS. He or she will have work experience with at least a few languages and platforms, Java, Hadoop, C#, .NET, Objective-C, Python, Django, Ruby on Rails, Javascript, etc., as well as with databases (SQLServer, MySQL, or Hbase).
Strengths in the followings areas would be a plus
- Experience in running studies with users from crowdsourcing platforms (e.g., Crowdflower, Mechanical Turk);
- Industry experience in developing and deploying collaborative applications as part of a team;
- Ability to develop applications that span multiple platforms (mobile, web, and desktop);
- Experience in parallel programming and large-scale data analytics using packages;
- Experience in running studies on prototypes for knowledge workers;
- Experience in user interface development, including iterative prototyping from early proof-of-concepts to interfaces mature enough for transfer to a product team.
Please send your CV with the coordinates of two referees we can contact for recommendation letters.
For further details, please contact Cedric Archambeau (cedric.archambeau@xrce.xerox.com), Guillaume Bouchard (guillaume.bouchard@xrce.xerox.xom) or Gregorio Convertino (gregorio.convertino@xrce.xerox.com).
Xerox Research Centre Europe (XRCE) is a young, dynamic research organization, which creates innovative technologies to support growth in Xerox business process outsourcing and document management services businesses.
Our domains of research stretch from the social sciences to computer science. We have renowned expertise in machine learning, natural language processing, computer vision, ethnography and services computing.
XRCE is part of the Xerox Innovation group made up of 800 researchers and engineers in four world-renowned research and technology centres. Xerox and XRCE is an equal opportunity employer.
The "Charte de la diversité”, adopted by Xerox, proves our engagement in favour of cultural, ethnic and social diversity. Our main building is compliant with the AGEFIPH standards for disabled access.
The Grenoble site is set in a park in the heart of the French Alps in a stunning location only a few kilometers from the city centre. The city of Grenoble has a large scientific community made up of national research institutes (CNRS, Universities, INRIA) and private industries. Stimulated also by the presence of a large student community, Grenoble has become a resolutely modern city, with a rich heritage and a vibrant cultural scene. It is a lively and cosmopolitan place, offering a host of leisure opportunities. Winter sports resorts just half an hour from campus and three natural parks at the city limits make running, skiing, trekking, climbing and paragliding easily available.
Grenoble is close to both the Swiss and Italian borders.