Predictive Analytic on Human Resource Department Data Based on Uncertain Numeric Features Classification

Authors

  • Asrul Huda Universitas Negeri Padang, Padang, Indonesia asrulhuda@gmail.com
  • Noper Ardi Universitas Negeri Padang, Padang, Indonesia noper.ardi@gmail.com

DOI:

https://doi.org/10.3991/ijim.v15i08.20907

Keywords:

Predictive Analytic, Naïve Bayes, Business Intelligence, Human Resource

Abstract


Business Intelligence is very popular and useful for a better understanding of business progress these days, and there are many different methods or tools being used in Business Intelligence. It uses combination of artificial intelligence, data mining, math, and statistic to gain better understanding and insight on the business process performance. As employees have an important role in business process, the desire to have a tool for classifying and predicting their wages are desirable. In this research, we tried to analyzed dataset from Human Resource Department, and this dataset can be used to analyst the data in order to draw a conclusion about whether any employees would prematurely leave the company, and then, a preventive action based on those parameters can be proposed. This is a kind of predictive analytic system which bases on Naïve Bayes, and it can predict whether an employee would leave or stay according to his or her characteristics. But the Naïve Bayes itself does not enough. So we develop a way to solve the problem using uncertain Numeric features classification on it. The accuracy of the result is depended on the amount and effectiveness of the training sets.

Author Biographies

Asrul Huda, Universitas Negeri Padang, Padang, Indonesia asrulhuda@gmail.com

Universitas Negeri Padang, Padang, Indonesia

asrulhuda@gmail.com

Noper Ardi, Universitas Negeri Padang, Padang, Indonesia noper.ardi@gmail.com

Universitas Negeri Padang, Padang, Indonesia

noper.ardi@gmail.com

Downloads

Published

2021-04-23

How to Cite

Huda, A., & Ardi, N. (2021). Predictive Analytic on Human Resource Department Data Based on Uncertain Numeric Features Classification. International Journal of Interactive Mobile Technologies (iJIM), 15(08), pp. 172–181. https://doi.org/10.3991/ijim.v15i08.20907

Issue

Section

Short Papers