Use of Machine Learning for an Automated Approach to Human Capabilities Screening
Sunil Bhutada1, Saylee Morey2
1Dr. Sunil Bhutada, Department of Information Technology, Sreenidhi Institute of Science & Technology Yamnampet, Ghatkesar Hyderabad, Telangana, India.
2Saylee Morey, Department of Information Technology, Sreenidhi Institute of Science & Technology Yamnampet, Ghatkesar Hyderabad, Telangana, India.
Manuscript received on 08 April 2019 | Revised Manuscript received on 15 April 2019 | Manuscript Published on 24 May 2019 | PP: 408-412 | Volume-8 Issue-6S3 April 2019 | Retrieval Number: F10820486S319/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Machine Learning (ML) is paradigm that constantly learns by means of collecting past knowledge that makes use of historical data to know and trouble shooting. ML is a key enabler of Artificial Intelligence (AI). It is the contemporary method to virtual transformation making our computing method more efficient, cost powerful and dependable. ML algorithms are grouped based on their purpose a) Supervised learning b) Unsupervised learning c) Reinforcement learning. This project consists of assessment of human skills based on historic statistics. ‘Capabilities’ is the conceptualization for interpersonal comparisons of the capabilities to carry out a mission. Here the emphasis is on bridging the distance between qualitative and quantitative methods to classify talent assessment of human beings and produce report in statistical shape. This research applies machine-learning algorithms to information accrued after talent exams are taken by using applicants. A getting to know module might be built as a way to help subject matter experts (SMEs) to attain the computed assessment end result. These rankings could be used to improve the device and over a period of time the device gets better at assessing the evaluations. This approach will help pre-screening to be extra effective when evaluating applicants previous to induction into the device.
Keywords: PostgreSQL; Kafka; PySpark; Elastic Search; Kibana; Machine Learning; Docker.
Scope of the Article: Machine Learning