A Machine Learning Framework for Personalized Job Recommendation
Fuente:
Zenodo
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Recurso digital |
| Pubblicazione: |
Zenodo
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866902192326180864 |
|---|---|
| author | Rumana Hasinullah Shaikh Subhalaxmi Nayak |
| author_facet | Rumana Hasinullah Shaikh Subhalaxmi Nayak |
| contents | Resume Based Company Recommendation System streamlines and improves the manual placement processes. In today's competitive job market, the efficient classification of resumes plays a pivotal role in streamlining recruitment processes. The model helps new students to find best fit companies for them. Also, this research investigates the effectiveness of different machine learning models in classifying resumes focusing on two distinct methodologies for splitting the dataset: manual and automatic. The model is evaluated using three machine learning algorithms which are, K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Random Forest. Labelled datasets comprising resumes from multiple sources are utilized, with one manually splitting technique into training and testing sets and the other automatically spitting technique by the model. This model focuses on automating the process of matching students resumes with company. When a new resume is uploaded then the model recommends a company to that student. The study compares the accuracy of these models under both splitting methodologies and analyzes the impact of dataset partitioning on classification performance. Experimental results demonstrate varying degrees of accuracy across the models, with Random Forest achieving the highest accuracy manual splitting of training and testing dataset and SVM achieving the highest accuracy automatic splitting of training and testing dataset. The findings underscore the importance of dataset splitting techniques and provide insights into the selection of appropriate machine learning models for resume classification tasks. This research contributes to the optimization of recruitment processes and informs practitioners and researchers about effective strategies for resume classification leveraging machine learning techniques. |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_20393349 |
| institution | Zenodo |
| language | |
| publishDate | 2026 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | A Machine Learning Framework for Personalized Job Recommendation Rumana Hasinullah Shaikh Subhalaxmi Nayak Machine Learning algorithms Support Vector System Random Forest Splitting techniques Resume Based Company Recommendation System streamlines and improves the manual placement processes. In today's competitive job market, the efficient classification of resumes plays a pivotal role in streamlining recruitment processes. The model helps new students to find best fit companies for them. Also, this research investigates the effectiveness of different machine learning models in classifying resumes focusing on two distinct methodologies for splitting the dataset: manual and automatic. The model is evaluated using three machine learning algorithms which are, K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Random Forest. Labelled datasets comprising resumes from multiple sources are utilized, with one manually splitting technique into training and testing sets and the other automatically spitting technique by the model. This model focuses on automating the process of matching students resumes with company. When a new resume is uploaded then the model recommends a company to that student. The study compares the accuracy of these models under both splitting methodologies and analyzes the impact of dataset partitioning on classification performance. Experimental results demonstrate varying degrees of accuracy across the models, with Random Forest achieving the highest accuracy manual splitting of training and testing dataset and SVM achieving the highest accuracy automatic splitting of training and testing dataset. The findings underscore the importance of dataset splitting techniques and provide insights into the selection of appropriate machine learning models for resume classification tasks. This research contributes to the optimization of recruitment processes and informs practitioners and researchers about effective strategies for resume classification leveraging machine learning techniques. |
| title | A Machine Learning Framework for Personalized Job Recommendation |
| topic | Machine Learning algorithms Support Vector System Random Forest Splitting techniques |
| url | https://doi.org/10.5281/zenodo.20393349 |