Intelligent predictive hiring model and personality assessment

Title

Intelligent predictive hiring model and personality assessment

Creator

Sneha, Mishael; Raman, Gokulapriya; Vetriveeran, Divya

Description

Selecting the right candidates is essential for organisational success, yet traditional hiring methods often fall short. This research introduces an advanced approach integrating natural language processing (NLP), personality assessment, and deep learning to improve candidate selection. NLP extracts key attributes from job descriptions and resumes, while personality assessments evaluate candidate suitability. A fusion of LSTM and RNN models predicts job fit using a dataset of job roles, resumes, and MBTI personality types. Pre-processing includes tokenisation, encoding, and data splitting for training and testing. The model architecture combines embedding layers with LSTM units, optimised using binary cross-entropy loss and accuracy metrics. Results show that this fusion model outperforms traditional algorithms, improving job matching accuracy. This research enhances recruitment by leveraging AI-driven insights. Future work will refine predictive models, integrate additional data, and address ethical concerns to ensure fairness and transparency, fostering a more efficient and equitable hiring process. Copyright 2026 Inderscience Enterprises Ltd.

Source

International Journal of Work Organisation and Emotion;Volume;17;Issue;2026-03-01 00:00:00;pp.180-203

Date

01-01-2026

Publisher

Inderscience Publishers

Subject

deep neural networks; intelligent hiring; natural language processing; NLP; personality assessment

Coverage

Sneha M., Department of Computer Science and Engineering, Sri Manakula Vinayagar Engineering College, Pondicherry, India; Raman G., Department of Computer Science and Engineering, Christ University, Bangalore, India; Vetriveeran D., Anna University, University College of Engineering, Thirukkuvalai, India

Rights

Restricted Access; Hardcopy may be available in the library

Relation

ISSN: 17408938;

Format

online

Language

English

Type

Article

Identifier

https://doi.org/10.1504/IJWOE.2026.153667

https://www.scopus.com/pages/publications/105039781243?origin=resultslist