In anticipation of his upcoming presentation at Predictive Analytics World Industry 4.0, part of Machine Learning Week, June 18-22, 2023 in Las Vegas, we asked Alejandro Jesús Castañeira Rodriguez, Principal Data Scientist at
JANZZ Ltd., a few questions about his presentation, AI Meets Human Resources, — see what’s in store at the PAW Industry 4.0 conference.
Q: In your work with predictive analytics, what behavior or outcome do your models predict?
A: At Janzz Technology we try to generate meaningful suggestions for job seekers and employment companies in an interpretable and unbiased way. Also, we provide real-time analytics of Human Resources information for broad population sectors, where governments and international entities can measure the skill gap between educational systems and labor markets.
Q: How does machine learning deliver value to Janzz – what is one specific way in which it actively drives decisions or operations?
A: Machine Learning methods bring additional value to Janzz and the Human Resources industry in general, as they provide support for better job searches, reduce the time for candidates screening, and help to eliminate biases. They allow to make decisions based only on a candidate’s competencies and automatically discard irrelevant characteristics such as gender, race, etc., which brings more transparency to hiring procedures.
Q: Can you describe a quantitative result, such as the predictive lift of your model or the ROI of an analytics initiative?
A: It is good to notice that our solutions are meant to speed up and enhance screening and search process, not to automate them, consequently, all interviews and hiring decisions will always be made by a human. In this sense, the screening time required by a recruiter to fill a high-demanded position (+100 applications) using our systems is reduced by 20x. Also, the possibility of a higher recall of job openings, which means candidates finding more opportunities, and not missing job positions because of incorrect keyword searches or bad SEO optimization, it goes up by 15x using our matching engine.
Q: What surprising discovery or insight have you unearthed in your data?
A: Some insights from our processed data are that frequently mentioned competencies are not necessarily crucial requirements, this applies to most mentioned HR terms, such as: Microsoft Office, Team player, Organization skills, etc., where in a constantly evolving labor market new skills and technologies make more distinctive differentiators for a new hire. Also, an increased number of current advertisements for a given occupation is not necessarily an indicator of future availability. The same applies for skills requirements.
Q: Sneak preview: Please tell us a takeaway that you will provide during your talk at Machine Learning Week.
A: In this talk, you will observe how several Natural Language Processing techniques and different Deep Learning models can be applied and synergized, to create a novel and completely explainable Recommender System for the Human Resources industry.
Don’t miss Alejandro’s presentation — Click here to register for attendance.
 |
 |
 |
