FoDRA — A new content-based job recommendation algorithm for job seeking and recruiting

Almalis, Nikolaos D.; Tsihrintzis, George A.; Karagiannis, Nikolaos; Strati, Aggeliki D.

doi:10.1109/iisa.2015.7388018

Cited by 35 publications

(12 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These limitations motivated and guided our research. In our previous work, we described the problem of job seeking in a formal way and proposed a high-level architecture of a constrain-based JRS using the four dimensional recommendation algorithm (FoDRA) (Almalis et al, 2015b). In this article, we also use FoDRA to compute suitability, and we propose the introduction of the minimum acceptable suitability level (Section 3) to deal with the crowd avoidance problem which appears in many to many (N-N) types of job seeking and recruiting.…”

Section: Job Recommendation Systemsmentioning

confidence: 99%

“…All these generic approaches were summarised in our previous work (Almalis et al, 2015b) and they were formulated in a description which is the concrete and formal definition of the job seeking and recruiting problem: "Let J be the set of all jobs and let P be the set of all possible candidate employees/job seekers (people) that can be recommended. Let f be a utility function, which measures the suitability of a candidate employee P for a job J that is f: J × P → R, where R is a totally ordered set (for example, real numbers within a certain range).…”

Section: Entities Relationsmentioning

confidence: 99%

“…For example, a candidate having six or seven years of experience is probably more suitable for a job position that requires at least five years of past working experience than a candidate with exactly five years. Also a job recruiter might prefer other attributes being under a certain limit (i.e., age) (Almalis et al, 2015b). Although many recommendation approaches tried to solve the above problems (as outlined in Section 2), the quality of their results still remains a challenge.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Handling the crowd avoidance problem in job recommendation systems integrating FoDRA

Almalis

Tsihrintzis

2020

IJCISTUDIES

Self Cite

View full text Add to dashboard Cite

In this article, we present the basic principles and approaches of job recommender systems (JRSs). Furthermore, we describe the four different relation types of the job seeking and recruiting problem, derived directly from the formal definition of JRSs. We use our previously published four dimensions recommendation algorithm (FoDRA) to calculate the suitability of a person for a job and then we model a job seeking and recruiting problem consisting of many candidates and many jobs (N-N case). Finally, we test the algorithm and present the results proposing a solution -the minimum acceptable suitability level -for the crowd avoidance problem that occurs. Our study produces good results and shows that this approach can be considered as an important asset in the domain of job seeking and recruiting.

show abstract

Section: Job Recommendation Systemsmentioning

confidence: 99%

Section: Entities Relationsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Handling the crowd avoidance problem in job recommendation systems integrating FoDRA

Almalis

Tsihrintzis

2020

IJCISTUDIES

Self Cite

View full text Add to dashboard Cite

show abstract

“…Unlike standard MF models, Bayesian personalized ranking (BPR) tries to preserve users' preference between two items (Rendle et al 2009). BPR is reported to perform better than many other MF models such as singular value decomposition (SVD) (Almalis et al 2015;Rendle et al 2009), and has been successfully applied in many applications, such as media recommendation ) and friend recommendation in social network (Ding et al 2017). BPR is also adopted in this paper for job recommendation.…”

Section: Collaborative Filteringmentioning

confidence: 99%

“…At present, career centers of institutions and colleges mainly provide manual job recommendation to graduates based on information from questionnaire surveys (Al-Otaibi and Ykhlef 2012; Nguyen et al 2013). Other graduate job recommendation systems are implemented based on the similarity calculation (Almalis et al 2015;Liu et al 2017;Patel and Kakuste 2017;Razak et al 2014). For example, Patel and Kakuste (2017), Razak et al (2014) have proposed a job recommendation system, which match the similarity between the skills extracted from a resume and the skills required by a job.…”

Section: Graduate Job Recommendationmentioning

confidence: 99%

Job recommendation algorithm for graduates based on personalized preference

Zhou

Liao

Chen

et al. 2019

CCF Trans. Pervasive Comp. Interact.

View full text Add to dashboard Cite

It is challenging for graduates to find a proper job. Unlike those with occupational history, graduates generally are short of work experience and the support from social network, so they have to face hundreds of recruitment companies. The process of applying for a job is time-consuming, especially in preparing and attending tests and interviews. Not knowing which companies are most proper for them, graduates need to devote their energy and time to preparing for each potential recruitment. This job-hunting strategy can easily lead to employment dissatisfaction or failure. Therefore, it is very helpful to recommend a few most suitable jobs to graduates. Collaborative filtering (CF) method is currently the most frequently adopted and effective recommendation algorithm, but it cannot be directly applied to job recommendation for graduates because graduates generally have no historical records on employment. Besides, job recommendation should take into account graduate preferences for jobs, such as enterprise types and company locations, which are crucial to job choices. To address these challenges, we first analyze the pattern of job choices of graduates. Based on this, we propose a personalized preference collaborative filtering recommendation algorithm (P2CF), which can not only recommend jobs for graduates through massive campus records, but also identify graduate personal preferences for jobs. Graduates are first clustered into different groups according to their academic performances and family economic conditions. Then Bayesian personalized ranking (BPR) method is introduced to calculate the scores of graduate groups to jobs. Finally the scores and graduate personalized preferences are combined to recommend a few potential jobs. P2CF is a recommendation algorithm with hierarchical structure, which takes account of both the group records of job choices and the individual preferences for jobs. Experimental results show that P2CF on job recommendation outperforms state-of-the-art CF methods and identifies graduate personalized preference for jobs accurately.

show abstract

CVO: Curriculum Vitae Optimization by Recommending Keywords to Undergraduate Students

Santos

Góes

Martins

2023

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

FoDRA — A new content-based job recommendation algorithm for job seeking and recruiting

Cited by 35 publications

References 14 publications

Handling the crowd avoidance problem in job recommendation systems integrating FoDRA

Handling the crowd avoidance problem in job recommendation systems integrating FoDRA

Job recommendation algorithm for graduates based on personalized preference

CVO: Curriculum Vitae Optimization by Recommending Keywords to Undergraduate Students

Contact Info

Product

Resources

About