Authors :
Sandhya Sheshadri; Hemant Palivela
Volume/Issue :
Volume 8 - 2023, Issue 6 - June
Google Scholar :
https://bit.ly/3TmGbDi
Scribd :
https://tinyurl.com/4ad6es3u
DOI :
https://doi.org/10.5281/zenodo.8208010
Abstract :
Introduction –
Human capital informatics is a computation
technique to People management. Human Resource
Planning has advanced tremendously during the last
century. It evolved from a strategic to a fundamental
strategy. It enables your firm to measure the impact of a
selection of HR KPIs on organizational effectiveness and
adopt data-driven judgments.
Purpose –
HR is expected to accomplish objectives, the
function of HR is shifting from data collection to data
interpretation. HR is, unfortunately, one of the most
under-resourced areas in most companies. Machine
Intelligence in HR Resource management helps
businesses run effectively and successfully. HR
departments can make smarter judgments, eliminate
prejudices, and boost productivity in their businesses.
So, the major goal here is to provide organizations with
the best job seekers depending on their skill preferences
and potential business places.
Methodology –
Using different matching techniques, we can
achieve a proper set of candidates for firms that have
some set of skills or subjects listed and the candidates
are also experienced in those skills or subjects. Here we
are trying to match skills of students with company
required skills and then we are using different
constraints with skills preference matching like location
and Myers-Briggs Type Indicator (MBTI). Statistical
techniques for matching like Multiple Preferences
Matching Algorithm (MPMA) will be utilized for the
matching process. Competing with the present statistical
models we have employed other machine learning
techniques like word-2-vec and latent semantic
techniques.
Findings –
After performing Skill Preference Matching, we
have concluded that MPMA is giving better results Now
we are looking for other points to capture like match
quality, global search, and controllability.
Keywords :
Artificial Intelligence, Human Resource Analytics, Human Resource Management, Semantic Analysis, Statistical Models
Introduction –
Human capital informatics is a computation
technique to People management. Human Resource
Planning has advanced tremendously during the last
century. It evolved from a strategic to a fundamental
strategy. It enables your firm to measure the impact of a
selection of HR KPIs on organizational effectiveness and
adopt data-driven judgments.
Purpose –
HR is expected to accomplish objectives, the
function of HR is shifting from data collection to data
interpretation. HR is, unfortunately, one of the most
under-resourced areas in most companies. Machine
Intelligence in HR Resource management helps
businesses run effectively and successfully. HR
departments can make smarter judgments, eliminate
prejudices, and boost productivity in their businesses.
So, the major goal here is to provide organizations with
the best job seekers depending on their skill preferences
and potential business places.
Methodology –
Using different matching techniques, we can
achieve a proper set of candidates for firms that have
some set of skills or subjects listed and the candidates
are also experienced in those skills or subjects. Here we
are trying to match skills of students with company
required skills and then we are using different
constraints with skills preference matching like location
and Myers-Briggs Type Indicator (MBTI). Statistical
techniques for matching like Multiple Preferences
Matching Algorithm (MPMA) will be utilized for the
matching process. Competing with the present statistical
models we have employed other machine learning
techniques like word-2-vec and latent semantic
techniques.
Findings –
After performing Skill Preference Matching, we
have concluded that MPMA is giving better results Now
we are looking for other points to capture like match
quality, global search, and controllability.
Keywords :
Artificial Intelligence, Human Resource Analytics, Human Resource Management, Semantic Analysis, Statistical Models
