Abstract
The most challenging problem in human resources specially in the IT digital services company, is to assign the best collaborator’s in the adequate project , then ensure the delivery’s performance.in this paper we aim to develop à recommandation System using based-content and collaborative filtering in order to recommend potential profiles for a new job offer. The Principal parts of this recommandation is the matching between job offer of new project and collaborators profiles and the scoring using AHP method. In the first step we propose a model of criteria to measure collective skills , we validate by a survey realized in the IT service company , we analyze the data collected using PCA method (Principal Component Analysis).the results indicate six factors to measure collective skills of each collaborator (Technical skill, Proactivity ,Integrity, Cooperation, Communication and Benevolence/Interpersonal Relationship), these factors are used in AHP function to give score for each collaborator then allow the recommendation for the adequate project.
Highlights
In the Digital services company, In Human Resources domain, one of the most challenging problems is to affect the best profiles to the adequate project, to predict the success of collaborator and to ensure the delivery’s performance
The importance of trust for the team’s performance, the criteria of trust are (Integrity, Benevolence, technical skill), we note that these criteria are related to the Trust Model MDS (Mayer, David, Shoorman).Our proposition aims to take into account the trust in the measure of collective skills, we propose a hybrid model that assembles these two models, we examine the validity of this proposition by a survey carried out in an IT Digital services company, the objective of this survey is to define the criteria to measure collective skills from the analysis of the collected data using PCA method
In the E-recruitment, we find many works in this field, we note the work (Casagrande et al, 2017), the author proposes a recommendation system using content-based filtering, it is possible to target relevant candidate profiles using the information provided by the recruiter without, to rely on candidate reviews by other recruiters. he uses the matching of the job offer and candidate profile by the indexation and full text search using the engine LUCENE, for ranking the candidate he uses a sousscoring related to similarity of titles, number of skills, the difference between an experiences year of candidate and job offer. he progresses the accuracy of the system using the automatic detection of the activity area with supervised machine learning
Summary
In the Digital services company, In Human Resources domain, one of the most challenging problems is to affect the best profiles to the adequate project, to predict the success of collaborator and to ensure the delivery’s performance. The measure of collective skill is taken into account through various studies. We quote on one hand the study of Janaina Macke (2016), who present an instrument to measure collectives skills in IT team and indicate four factors (Proactivity, Cooperation, Communication and InterpersonalRelationship), on the other hand the study of Lucile Callebert (2017) who elaborate a multi-agent system that generates the behaviors of agents on the team in a virtual environment, he highlights. The importance of trust for the team’s performance, the criteria of trust are (Integrity, Benevolence, technical skill) , we note that these criteria are related to the Trust Model MDS (Mayer, David, Shoorman).Our proposition aims to take into account the trust in the measure of collective skills, we propose a hybrid model that assembles these two models, we examine the validity of this proposition by a survey carried out in an IT Digital services company, the objective of this survey is to define the criteria to measure collective skills from the analysis of the collected data using PCA method. The structure of this paper is as follows: First, we introduce the literature review, our contribution, we discuss the results, conclude in the final section indicating the perspectives of our contribution
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Artificial Intelligence and Machine Learning
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
