Recommendation System for Human Resource Management by the Use of Apache Spark Cluster

Azamat Serek, Kamila Orynbekova, Assem Talasbek, Darmen Kariboz, Gulnara Saimassay, Andrey Bogdanchikov

2023

DOI 10.1109/icecco58239.2023.10147129

Data confidence 85 high

How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

In this paper, there has been built and tested recommendation systems for recommending new positions for employees on Apache Spark by the use of a cluster of physical servers. The cluster has been built in the university, and the code has been executed both on a cluster, google colab, and a standalone mode. It was shown that the current cluster spends more time on the execution in comparison with colab, but as new servers get added to the cluster and the size of dataset is to increase, the performance will be much faster in comparison with colab. It can be valuable in HR departments which wish to use their own servers for the security purposes.