Grant: Engage Grants Program
University of Alberta
$23,000.00
Automated matching of applicants to job descriptions
EF 2016-17
Résumé
Processing applicants for a job is a demanding and labour-intensive process. The goal of this task is to automate the process assessing the fitness of an applicant for a job, based on the applicant's submitted resume, and the job description, in such a way that the assessment of the automated system would agree as closely as possible with a human evaluator. In particular, the output of the system would be a ranked list, with the most suitable applicants at the top. A feature-based approach will be used, with a large portion of the research project being based on identifying relevant, informative features of the resumes under consideration. Features will be drawn from text analytics, parsing, named entity recognition, and sentiment analysis tools. Feature sets will be evaluated using machine learning methods. The product of this research will be a system which our industry partner HireGround can use to process applicants more efficiently; if we can create an algorithm which consistently agrees with a human evaluator, than work hours can be saved by performing an initial appraisal of the set of applicants by applying the algorithm, rather than performing this step manually.Since the end result of the project will be software, developed with the cooperation and feedback of HireGround staff, our industry partner will be able to integrate the software into their services, providing an advantage not only to HireGround, but to their Canadian clients as well. The average number of applicants per job has, in recent years, increased from approximately 250, to between 800 and 1500, creating an increased demand for applicant processing and tracking services. With the completion of this project, HireGround will have a new tool at their disposal to quickly process large numbers of job applicants for its clients, putting them in a better position to meet this demand. Combined with the research and industry experience for the research team, the project will provide a net benefit to a wide variety of Canadian individuals and organizations.
Programme
Engage Grants Program
Bénéficiaire
Emplacement
Alberta, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
493545-2016
Name nom
Kondrak, Grzegorz
Department département
Computing Science
Organization id
9
Institution établissement
University of Alberta
Province en
Alberta
Province fr
Alberta
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2016
Competition year année de concours
2016
Award amount
23000
Program id
EGP
Program name en
Engage Grants Program
Program name fr
Programme de subventions d'engagement partenariat
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1555
Committee name en
Prairie Internal Decision Committee
Committee name fr
Comité de décision interne pour les Prairies
Area of application code
802
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Information systems and technology
Area of application fr
Systèmes d'information et technologie de l'information
Research subject code
2801
Research subject group en
Artificial intelligence
Research subject group fr
Intelligence artificielle
Research subject en
Natural language and speech understanding
Research subject fr
Langage naturel et reconnaissance de la parole
Partie
1
Nb partie
1
Application title
Automated matching of applicants to job descriptions
Keyword
NSERC
Application summary
Processing applicants for a job is a demanding and labour-intensive process. The goal of this task is to automate the process assessing the fitness of an applicant for a job, based on the applicant's submitted resume, and the job description, in such a way that the assessment of the automated system would agree as closely as possible with a human evaluator. In particular, the output of the system would be a ranked list, with the most suitable applicants at the top. A feature-based approach will be used, with a large portion of the research project being based on identifying relevant, informative features of the resumes under consideration. Features will be drawn from text analytics, parsing, named entity recognition, and sentiment analysis tools. Feature sets will be evaluated using machine learning methods. The product of this research will be a system which our industry partner HireGround can use to process applicants more efficiently; if we can create an algorithm which consistently agrees with a human evaluator, than work hours can be saved by performing an initial appraisal of the set of applicants by applying the algorithm, rather than performing this step manually.Since the end result of the project will be software, developed with the cooperation and feedback of HireGround staff, our industry partner will be able to integrate the software into their services, providing an advantage not only to HireGround, but to their Canadian clients as well. The average number of applicants per job has, in recent years, increased from approximately 250, to between 800 and 1500, creating an increased demand for applicant processing and tracking services. With the completion of this project, HireGround will have a new tool at their disposal to quickly process large numbers of job applicants for its clients, putting them in a better position to meet this demand. Combined with the research and industry experience for the research team, the project will provide a net benefit to a wide variety of Canadian individuals and organizations.