Job Offers Classifier using Neural Networks and Oversampling Methods

TL;DR

This paper presents a neural network-based classifier for job offers that employs oversampling techniques to handle class imbalance, achieving high accuracy across 23 job categories using data from Mexico's largest job bank.

Contribution

The study introduces a novel combination of deep learning and synthetic oversampling methods for automatic job classification in a large-scale, multi-class setting.

Findings

Geometric-SMOTE improved classification performance.

Deep learning models outperformed traditional machine learning algorithms.

Best results achieved with convolutional neural network and Geometric-SMOTE.

Abstract

Both policy and research benefit from a better understanding of individuals' jobs. However, as large-scale administrative records are increasingly employed to represent labor market activity, new automatic methods to classify jobs will become necessary. We developed an automatic job offers classifier using a dataset collected from the largest job bank of Mexico known as Bumeran https://www.bumeran.com.mx/ Last visited: 19-01-2022.. We applied machine learning algorithms such as Support Vector Machines, Naive-Bayes, Logistic Regression, Random Forest, and deep learning Long-Short Term Memory (LSTM). Using these algorithms, we trained multi-class models to classify job offers in one of the 23 classes (not uniformly distributed): Sales, Administration, Call Center, Technology, Trades, Human Resources, Logistics, Marketing, Health, Gastronomy, Financing, Secretary, Production, Engineering, Education, Design, Legal, Construction, Insurance, Communication, Management, Foreign Trade, and Mining. We used the SMOTE, Geometric-SMOTE, and ADASYN synthetic oversampling algorithms to handle imbalanced classes. The proposed convolutional neural network architecture achieved the best results when applied the Geometric-SMOTE algorithm.