Design and develop an intelligent recommendation system : job candidate recommender for ITC industry in Hong Kong

Pao Yue-kong Library Electronic Theses Database

Design and develop an intelligent recommendation system : job candidate recommender for ITC industry in Hong Kong

 

Author: Lam, Sze Wang
Title: Design and develop an intelligent recommendation system : job candidate recommender for ITC industry in Hong Kong
Degree: M.Sc.
Year: 2016
Subject: Hong Kong Polytechnic University -- Dissertations
Employees -- Recruiting -- China -- Hong Kong.
Employee selection -- Data processing.
Expert systems (Computer science)
Computer industry -- Employees.
Department: Dept. of Computing
Pages: ix, 128 pages : color illustrations
Language: English
InnoPac Record: http://library.polyu.edu.hk/record=b2857291
URI: http://theses.lib.polyu.edu.hk/handle/200/8386
Abstract: One of the common problem faced by the recruiters of Information Technology and Communication industry is difficult to select suitable candidates from the number of resumes received. Firstly, it is a time consuming task for screening a lot of unstructured format resumes. Secondly, since the skill terms and knowledge in this industry change frequently, given that there is no perfect candidate who fulfill all the requirements, it is difficult for recruiter to select candidate who has related knowledge and skill. Job Matcher was designed as an intelligent recommender to recommend suitable candidates for recruiters by analyzing the unstructured data of job post and resumes in a cost effective way. It calculates the similarity between each job post and resumes semantically with the pre-built ontology as the common vocabulary. This ontology-based information system provides a more flexible query than the traditional keyword-based approach. Two domain experts tested the precision rate of Job Matcher by ranking a same set of resumes in term of the candidates' suitability to a job. The result showed that Job Matcher can recommend suitable candidates in an acceptable level, however, it failed to generate a very precise result as the domain experts ranked. Other factors, such as previous working experience, expected salary and notice period, affected the precision rate had been discussed. Some valuable lesson learned and future works were suggested for the next development.

Files in this item

Files Size Format
b28572919.pdf 2.939Mb PDF
Copyright Undertaking
As a bona fide Library user, I declare that:
  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
  3. I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.

     

Quick Search

Browse

More Information