Enhancing Recruitment Efficiency in HRM through Intelligent Resume Screening and Job Matching Using Fuzzy Logic and Ensemble Learning
Bibliographic record
Abstract
The increasing number of job applications on digital recruitment platforms is a problem for human resource managers, who have to balance efficiency with equity in candidate evaluation. Conventional resume screening systems frequently show restricted interpretability and inadequate matching precision. The proposed study introduces a hybrid recruitment model that combines fuzzy logic and ensemble learning to provide intelligent and explainable candidate-job matching. Fuzzy logic integrates recruiter selection patterns through interpretable membership functions and rule sets, while the ensemble architecture utilises models like Random Forest, Gradient Boosting, and XGBoost to improve predicting accuracy. The system was subjected to extensive evaluation using curated Kaggle recruitment datasets, benchmarked against established baseline models. Experimental results demonstrated substantial performance enhancements, with nDCG@10 = 0.964, Precision@5 = 0.948, Recall@5 = 0.931, MAP = 0.957, AUC = 0.981, and RMSE = 0.082, outperforming conventional methodologies. The suggested approach automates extensive screening while ensuring openness, allowing HR experts to track decisions to comprehensible rules. The suggested study integrates powerful machine learning with human-aligned reasoning to improve the efficiency and lack of trust in AI-driven recruitment platforms. Its use could optimise talent acquisition processes, reduce bias, and enhance recruitment results across several industry sectors.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".