Banca de DEFESA: ALAN DA SILVA CARDOSO

Uma banca de DEFESA de MESTRADO foi cadastrada pelo programa.
DISCENTE : ALAN DA SILVA CARDOSO
DATA : 17/02/2020
HORA: 09:30
LOCAL: Sala 1.05 Campus CTAN
TÍTULO:
THE MATCHING SCARCITY PROBLEM: WHEN RECOMMENDERS DO NOT CONNECT EXTREMES TO RECRUITMENT SERVICES


PALAVRAS-CHAVES:

-


PÁGINAS: 93
GRANDE ÁREA: Ciências Exatas e da Terra
ÁREA: Ciência da Computação
RESUMO:
Connect candidates and jobs to promote real placement opportunities is one of the most impacting and challenging scenarios for Recommendation Systems (SsR). A major concern when creating SRs for recruitment services is to ensure placement opportunities for all applicants and job openings as quickly possible, avoiding financial losses for both sides. We refer to these scenarios where candidates or jobs suffer from a lack of correspondence in the system like Problem of Matching Scarcity (PMS). This paper presents the PMS, discussing the reasons why we consider it a recurring threat to recruitment and presenting new strategies to identify, characterize and mitigate PMS in real scenarios. Experimental evaluations on real data from Catho, a company recruitment leader in Latin America, showed that curricula tend to be less well written than job descriptions, displaying various information irrelevant. Replacing this information appropriately with useful information reduces up to 50% the number of CVs and vacancies that suffer from PMS.


MEMBROS DA BANCA:
Externo à Instituição - ADRIANO CÉSAR MACHADO PEREIRA - UFMG
Externo ao Programa - 2325597 - DIEGO ROBERTO COLOMBO DIAS
Presidente - 1674068 - LEONARDO CHAVES DUTRA DA ROCHA
Notícia cadastrada em: 11/02/2020 11:24
SIGAA | NTInf - Núcleo de Tecnologia da Informação - | Copyright © 2006-2024 - UFSJ - sigaa02.ufsj.edu.br.sigaa02