Butterfly Predictive Project: Big Data and Social Networks for E-recruitment
[preliminary translation to be completed, see French version which is more complete]
The RALI at Université de Montréal and its industrial partner LittleBigJob Networks Inc. develop a platform to improve the process of recruiting managers and high level technicians by exploiting Big Data on many aspects: improvement in harvesting and combining public data from social networks; improvement in the matching process between candidates and job offers; prediction of the success of a given candidate at a new position. This project relies on Big Data analysis gathered by the industrial partner both on the web and at its business partners while complying with the privacy of the candidates and making sure that internal recruitment strategies of industry are not revealed.
RALI applies in this new area its well-established expertise in natural language processing both in French and in English in order to build new lexical resources (specialized vocabularies and ontologies in the recruitment domain), to parse the specialized texts, to develop new algorithms for matching and sorting candidates and to predict the success of a candidate at a new position. The challenge is high given the fact that a huge amount of data of different types has to be dealt with: curriculum vitae, motivation letters, job descriptions and millions of profiles gathered from social networks and job sites. A part of the project deals with the automatic generation or authoring aid for personalized profiles who want to enhance their career.
The industrial partner benefits from the experience of RALI in the bilingual processing of natural language to embed intelligence within its online recruitment applications.
This three year project started in November 2014 and is supported by a Collaborative Research and Development Grant from the Natural Sciences and Engineering Research Council of Canada