Sharanaja Senthurvelautham
A machine learning-based job forecasting and trend analysis system to predict future job markets using historical data.
Senthurvelautham, Sharanaja; Senanayake, Nipuna
Authors
Nipuna Senanayake
Abstract
Over the last two decades, technological advancements have created more job markets and job opportunities than ever. With the ever-increasing demand, it has become vital for academic institutions and businesses to keep up with employment requirements. The problem is more severe for modern and rapidly evolving industries such as software development. This study implements a prediction system for job trends to enable job seekers, organizations, and academic institutions to understand and align their endeavors to match the market requirement. Employers can benefit from the system by using it to identify potential talent shortages and proactively address them. Policymakers can also use the system to understand the potential impacts of changes in the job market on the economy, enabling them to make informed decisions about supporting employment growth. The prediction is made possible by creating a rich dataset based on more than 522,180 job listings from the past 24 months in the software industry. The dataset is fed to a Bidirectional LSTM model to predict the future trends of the job market for various roles and technologies. Auto-aggressive prediction is implemented using the bi-directional LSTM model as this combination proves to produce the most accurate results after multiple quantitative analyses and evaluations. This study evaluated the proposed solution against known real-world data and it was concluded that the system can predict the job trend for at least the next 12 months with a relatively high accuracy of 95.71%.
Citation
SENTHURVELAUTHAM, S. and SENANAYAKE, N. 2023. A machine learning-based job forecasting and trend analysis system to predict future job markets using historical data. In Proceedings of the 8th IEEE (Institute of Electrical and Electronics Engineers) International conference for convergence in technology 2023 (I2CT 2023), 7-9 April 2023, Lonavla, India. Piscataway: IEEE [online], 10126233. Available from: https://doi.org/10.1109/I2CT57861.2023.10126233
Conference Name | 8th IEEE (Institute of Electrical and Electronics Engineers) International conference for convergence in technology 2023 ( I2CT 2023) |
---|---|
Conference Location | Lonavla, India |
Start Date | Apr 7, 2023 |
End Date | Apr 9, 2023 |
Acceptance Date | Mar 11, 2023 |
Online Publication Date | May 23, 2023 |
Publication Date | Dec 31, 2023 |
Deposit Date | Jun 22, 2023 |
Publicly Available Date | Jun 22, 2023 |
Publisher | Institute of Electrical and Electronics Engineers (IEEE) |
Book Title | Proceedings of the 8th IEEE (Institute of Electrical and Electronics Engineers) International conference for convergence in technology 2023 ( I2CT 2023) |
ISBN | 9798350334012 |
DOI | https://doi.org/10.1109/I2CT57861.2023.10126233 |
Keywords | Bi-directional LSTM; Deep learning; Job market; Trend; Software industry; Auto-aggressive prediction |
Public URL | https://rgu-repository.worktribe.com/output/1993436 |
Files
SENTHURVELAUTHAM 2023 A machine learning-based (AAM)
(519 Kb)
PDF
Copyright Statement
© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Downloadable Citations
About OpenAIR@RGU
Administrator e-mail: publications@rgu.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search