TY - GEN
T1 - Predicting Online Job Recruitment Fraudulent Using Machine Learning
AU - Mouri, Ishrat Jahan
AU - Barua, Biman
AU - Mesbahuddin Sarker, M.
AU - Barros, Alistair
AU - Whaiduzzaman, Md
N1 - Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
PY - 2023
Y1 - 2023
N2 - Employing individuals via the Internet has been a boon for businesses in the modern day. It is much simpler and more convenient than traditional recruitment methods. However, several scammers are abusing this platform, which may result in financial and privacy loss for job seekers and damage to the reputable organisation's name. In this research, we proposed a technique for detecting Online Recruitment Fraud (ORF). This model uses a publicly available dataset containing 17,780 job postings. We apply the four classification models to determine which classification model performs best for our suggested model. In this model, we use decision trees, random forests, Naive Bayes and logistic regression methods. We have estimated and evaluated the accuracy of several prediction systems. The random forest classifier provides the greatest accuracy, 97.16%, on our dataset. We have endeavoured to develop a method for detecting bogus recruiting postings.
AB - Employing individuals via the Internet has been a boon for businesses in the modern day. It is much simpler and more convenient than traditional recruitment methods. However, several scammers are abusing this platform, which may result in financial and privacy loss for job seekers and damage to the reputable organisation's name. In this research, we proposed a technique for detecting Online Recruitment Fraud (ORF). This model uses a publicly available dataset containing 17,780 job postings. We apply the four classification models to determine which classification model performs best for our suggested model. In this model, we use decision trees, random forests, Naive Bayes and logistic regression methods. We have estimated and evaluated the accuracy of several prediction systems. The random forest classifier provides the greatest accuracy, 97.16%, on our dataset. We have endeavoured to develop a method for detecting bogus recruiting postings.
KW - Classification model
KW - Machine learning
KW - Natural language processing
KW - Online recruitment fraud
UR - http://www.scopus.com/inward/record.url?scp=85151139802&partnerID=8YFLogxK
U2 - 10.1007/978-981-19-7753-4_55
DO - 10.1007/978-981-19-7753-4_55
M3 - Conference contribution
AN - SCOPUS:85151139802
SN - 9789811977527
T3 - Lecture Notes in Electrical Engineering
SP - 719
EP - 733
BT - Proceedings of 4th International Conference on Communication, Computing and Electronics Systems - ICCCES 2022
A2 - Bindhu, V.
A2 - Tavares, João Manuel
A2 - Vuppalapati, Chandrasekar
PB - Springer Science and Business Media Deutschland GmbH
T2 - 4th International Conference on Communication, Computing and Electronics Systems, ICCCES 2022
Y2 - 15 September 2022 through 16 September 2022
ER -