Dataset of 19,000 online job posts from 2004 to 2015
This repo was created for the HDSC’ 22 Premier Project: Real Life Machine Learning Topics
View our list of contributors here
The labor market is continuously evolving with the use of technology to advertise job openings, hence, the need to understand the demand for certain professions and job titles. There is also a need to identify skills that are most frequently required by employers, how the distribution of necessary skills changes over time, and make recommendations to job seekers and employers.
Learn more about the dataset here
The data collection and initial research was funded by the American University of Armenia’s research grant (2015).
The dataset consists of 19,000 job postings that were posted through the Armenian human resource portal CareerCenter. The data was extracted from the Yahoo! mailing group https://groups.yahoo.com/neo/groups/careercenter-am. This was the only online human resource portal in the early 2000s. A job posting usually has some structure, although some fields of the posting are not necessarily filled out by the client (poster). The data was cleaned by removing posts that were not job related or had no structure. The data consists of job posts from 2004-2015.
You can get more information here
Read all about the project here
Everything about the EDA process can be found here here