Open Access
Research Article
Fraud-Detect-Net : A deep learning and machine learning framework for detecting fake job postings
*Sonika MalikCorresponding authorSonika.malik@msit.inDepartment of Information Technology Maharaja Surajmal Institute of TechnologyJanak Puri, Delhi, 110058, IndiaView full profile → , Preet RatheePreetirathee@msit.inDepartment of Information Technology Maharaja Surajmal Institute of TechnologyJanak Puri, Delhi, 110058, IndiaView full profile → , Anupama Kaushikanupama@msit.inDepartment of Information Technology Maharaja Surajmal Institute of TechnologyJanak Puri, Delhi, 110058, IndiaView full profile → , Prabhjot Kaurprabhjot.kaur@msit.inDepartment of Information Technology Maharaja Surajmal Institute of TechnologyJanak Puri, Delhi, 110058, IndiaView full profile → , Akshay SinghAkshay.singh@msit.inDepartment of Information Technology Maharaja Surajmal Institute of TechnologyJanak Puri, Delhi, 110058, IndiaView full profile →
* Corresponding author · click or hover a name for details
- Received:
- 01 Apr 2025
- Published Online:
- 01 May 2026
- Article type:
- Research Article
- Language:
- EN
- Article no.:
- JIOS-2301
- Pages:
- 2109–2117
Abstract
This study presents a hybrid framework combining BERT embeddings with a Random Forest classifier to detect fraudulent job postings. To address the severe class imbalance between genuine and fake listings, multiple oversampling methods—including SMOTE, SMOTE Tomek, ADASYN, SMOTE-ENN, and random oversampling—were evaluated. Model performance was further optimized through hyperparameter tuning using Randomized Search. The system was assessed with key metrics such as precision, recall, F1-score, and AUC-ROC, ensuring a balanced evaluation. Results demonstrate that leveraging contextual language representations from BERT, together with data balancing strategies, significantly improves fraud detection accuracy. This approach highlights the effectiveness of integrating advanced NLP models with resampling techniques for reliable online job fraud detection.
Keywords
Subject Classifications
Primary 68T07
References
[1] S. Vidros, C. Kolias, G. Kambourakis, and L. Akoglu, “Automatic detection of online recruitment frauds: Characteristics, methods, and a public dataset,” Future Internet, vol. 9, no. 1, p. 6 (2017), doi: 10.3390/fi9010006.[2] S. Dutta and S. K. Bandyopadhyay, “Fake job recruitment detection using machine learning approach,” Int. J. Eng. Trends Technol., vol. 68, no. 4, pp. 48–53 (2020), doi: 10.14445/22315381/ijett-v68i4p209s.[3] B. Alghamdi and F. Alharby, “An intelligent model for online recruitment fraud detection,” J. Inf. Secur., vol. 10, no. 3, pp. 155–176 (2019), doi: 10.4236/jis.2019.103009.[4] S. Lal, R. Jiaswal, N. Sardana, A. Verma, A. Kaur, and R. Mourya, “ORFDetector: Ensemble learning-based online recruitment fraud detection,” in Proc. 12th Int. Conf. Contemporary Computing (IC3) , pp. 1–5 (2019), doi: 10.1109/IC3.2019.8844879.[5] I. M. Nasser, A. H. Alzaanin, and A. Y. Maghari, “Online recruitment fraud detection using ANN,” in Proc. Palestinian Int. Conf. Inf. Commun. Technol. (PICICT), pp. 13–17 (2021), doi: 10.1109/PICICT53635.2021.00015.[6] S. U. Habiba, M. K. Islam, and F. Tasnim, “A comparative study on fake job post prediction using different data mining techniques,” in Proc. 2nd Int. Conf. Robotics, Electrical and Signal Processing Techniques (ICREST), pp. 543–546 (2021), doi: 10.1109/ICREST51555.2021.9331230.[7] C. Lokku, “Classification of genuinity in job posting using machine learning,” Int. J. Res. Appl. Sci. Eng. Technol., vol. 9, no. 12, pp. 1569–1575 (2021), doi: 10.22214/ijraset.2021.39580.[8] O. Nindyati and I. G. B. Nugraha, “Detecting scam in online job vacancy using behavioral features extraction,” in Proc. Int. Conf. ICT for Smart Society (ICISS) (2019), doi: 10.1109/ICISS48059.2019.8969842.[9] G. O. Alandjani, “Online fake job advertisement recognition and classification using machine learning,” 3C TIC: Cuadernos de Desarrollo Aplicados a las TIC, vol. 11, no. 1, pp. 251–267 (2022), doi: 10.17993/3ctic.2022.111.251-267.[10] A. Gosain and S. Sardana, “Handling class imbalance problem using oversampling techniques: A review,” in Proc. Int. Conf. Advances in Computing, Communications and Informatics (ICACCI), pp. 79–85 (2017), doi: 10.1109/ICACCI.2017.8125820.[11] F. Akhbardeh, C. O. Alm, M. Zampieri, and T. Desell, “Handling extreme class imbalance in technical logbook datasets,” in Proc. 59th Annu. Meeting Assoc. Comput. Linguistics (ACL), pp. 5740–5754 (2021), doi: 10.18653/v1/2021.acl-long.312.[12] G. K. Yadav, A. K. Tiwari, V. K. Singh, A. Kumar, D. Varshney, and A. K. Senger, “Empirical algorithm to detect skin disease using deep convolution neural networks through mobilenet algorithm,” Journal of Information and Optimization Sciences, vol. 45, no. 4, pp. 1017–1027 (2024), doi: 10.47974/JIOS-1624.[13] J. David, J. Cui, and F. Rahimi, “Classification of imbalanced datasets using BERT embeddings,” Dalhousie University (2020). [Online]. Available: https://fatemerhmi.github.io/files/Classification_of_imbalanced_dataset_using_BERT_embedding.pdf.[14] Kanika, J. Singla, A. K. Bashir, Y. Nam, N. U. Hasan, and U. Tariq, “Handling class imbalance in online transaction fraud detection,” Computers, Materials & Continua, vol. 70, no. 2, pp. 2861–2877 (2022), doi: 10.32604/cmc.2022.019990.[15] S. Bansal, “Real/fake job posting prediction,” Kaggle Dataset (Feb. 2020), [Online]. Available: https://www.kaggle.com/datasets/shivamb/real-or-fake-fake-jobposting-prediction.[16] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” in Proc. NAACL-HLT, pp. 4171–4186 (2019).[17] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, “Attention is all you need,” in Advances in Neural Information Processing Systems (NeurIPS), pp. 5998–6008 (2017).[18] D. W. Bliss, S. Kraut, and A. Agaskar, “Transmit and receive space-time-frequency adaptive processing for cooperative distributed MIMO communications,” in Proc. IEEE Int. Conf. Acoustics, Speech and Signal Processing (ICASSP), pp. 5221–5224 (2012), doi: 10.1109/ICASSP.2012.6289097.
Views: 55Downloads: 10Citations: 0
