Hybrid Clustering and KNN for Job Recommendations Using Scraped Data

DOI

10.2991/978-94-6463-858-5_38How to use a DOI?

Keywords

Silhouette score; cosine similarity; k-Nearest Neighbors; clustering; K-means; web scraping; unsupervised learning; job recommendation; dimensionality reduction

Abstract

Due to the huge number of job advertisements created by the quick growth of online job portals, it is difficult for job searchers to locate opportunities that are relevant to them. In order to create a customized job recommendation system, this study introduces a hybrid unsupervised learning framework that combines k-Nearest Neighbors with clustering. Our method makes use of web-scraped, unlabeled data, in contrast to conventional recommendation systems that depend on tagged datasets. We use one-hot encoding, normalization, and Term Frequency-Inverse Document Frequency to preprocess employment variables including location, experience, skills, and pay. We use Truncated Singular Value Decomposition for dimensionality reduction in order to lessen the curse of dimensionality. Based on silhouette analysis, we compare four clustering algorithms: K-means, DBSCAN, Agglomerative Hierarchical, and Gaussian Mixture Models. K-means performs the best. Furthermore, with high similarity scores, our k-Nearest Neighbors-based recommendation system performs noticeably better than a random baseline. The outcomes show how well our hybrid unsupervised learning architecture works to provide an accurate and scalable job recommendation system.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - M. Narasimha Raju
AU  - Polisettti Mohana Lakshmi Rupa
AU  - Poturi M. Lakshmi Sree Harshitha
AU  - Shaik Jasmine
AU  - Vislavath Pavani
AU  - Yeddu Leena Rishitha
PY  - 2025
DA  - 2025/11/04
TI  - Hybrid Clustering and KNN for Job Recommendations Using Scraped Data
BT  - Proceedings of International Conference on Computer Science and Communication Engineering (ICCSCE 2025)
PB  - Atlantis Press
SP  - 431
EP  - 442
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-858-5_38
DO  - 10.2991/978-94-6463-858-5_38
ID  - Raju2025
ER  -