Scribd
Upload
7 views3 pages

ISE527 Proposal

Uploaded by

Didik Hariadi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
7 views3 pages

ISE527 Proposal

Uploaded by

Didik Hariadi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Decision Making using Machine Learning

Mohammed Ayub (g201707490)


Muhammad D. Al Firdausi (g202210120)
February 8, 2023

ISE 527: Decision Making


Instructor: Dr. Haitham Saleh

1 Introduction
Decision making is unavoidable phenomenon in human life whether it is in personal, managerial or political
aspects. But it becomes more complex when multiple conflicting criteria are to be considered. Nowadays in any
organization, human capital are regarded as the most valuable resources and retaining them is a competitive and
strategic advantage for the organization. This project aims to work on decision making in an organization’s human
resource (HR) problem. The concerned problems relate to the turnover of the employee and what factors that affect
the employee whether to stay or quit the organization. The application of a machine learning method to reveal the
turnover factor can help the decision maker such as manager to make a better decision.

2 Motivation
Control on employee turnover can lead to successful organization and gives more advantage in its competitiveness
since the strategic plan of the organization can be maintained for a long-term period [1]. If the prominent factors
of employee’s turnover were known, a better decision can be achieved in order to make a long-lasting relationship
between organization and its employees. Indirectly, turnover affects organization’s cost where its capital to hire,
train, and accommodate the employee is lost. Our idea is motivated by [1] and [2].

3 Scope
The proposed study will scrutinize IBM human resource dataset which includes up to almost 1500 records of
employee with total of 38 features and/or other related datasets. When data is ready for analysis after some cleaning
process, a machine learning method can be implemented to analyze which feature is more prominent than others and
then predict the employees’ decision on their position in the organization. The output of the method can be utilized
by HR manager to decide on which aspect the company should focus on for the sake of a better environment for

1
Figure 1: High level methodological pipeline. ET= Extra tree, XGBT= Extreme Gradient Boosting Tree,
LGBM=Light Gradient Boosting Machine, ANN = Artificial neural Network, CNN = Convolutional Neural Network,
RFE= Recursive feature elimination, GWO = Gray wolf optimizer, GA =Genetic Algorithm, AHP= Analytical Hi-
erarchical Process

employee for long-lasting relationship. Having mentioned that this study will be limited to Multiple-criteria decision-
making (MCDM) or multiple-criteria decision analysis (MCDA) for analysis of importance of different attributes to
decision making using machine and deep learning.

4 Problem Definition
The voluntary turnover which is marked by the willingness of knowledged and talented employee to quit the
organization while he/she is still needed, is a big concern for HR. It is even worse if the employee joined another
organization’s competitor when the ex-employee knew many aspects of his/her ex-organization and could give better
contribution in the new place. Therefore, retaining talented employee will actually keep the organization on its best
performance and it can be achieved by recognizing the causes of the turnover along with appropriate management
approach implementation which is widely believed can reduce the turnover rate. Therefore, this study will focus on
MCDA and machine learning techniques to identify the factors affecting in human resource turnover, and accordingly
we define the problems in two folds as follows:

1. To identify the importance of different attribute/criteria using different MCDA techniques, that
help managers take wise and strategic decision, and
2. To validate the results of the above methods applying them into different machine and deep
learning techniques.

5 Methodology
MCDA is an operations research sub-discipline that explicitly evaluates multiple conflicting criteria in decision
making. People usually weigh multiple criteria implicitly in their daily lives and may be content with the consequences
of such decisions made solely on intuition. But, effectively structuring complex problems and explicitly considering
multiple criteria leads to more informed and better decisions. On the other hands, machine learning techniques
that are based on learned model from data, are also playing a vital role in various fields including computer vision,
healthcare, decision making and many others. In this paper, both concepts are combined to determine the influencing
factors to determine turnover of employee in an organization. The high level methodological pipe line is depicted
in Fig. 1. The dataset will be cleaned and data samples are preprocessed before applying any MCDA techniques.
After that the results from each technique will be fed into respective machine/deep learning techniques as input to
help comprehend and understand decision makers the contribution of each attributes or criteria towards acceptable
decision making. From the classification outputs of machine/deep learning models, the decision makers can verify to
what extend the outputs of MCDA techniques are reliable in critical decision making of human resource retention.

2
References
[1] N. Pourkhodabakhsh, M. M. Mamoudan, and A. Bozorgi-Amiri, “Effective machine learning, meta-heuristic
algorithms and multi-criteria decision making to minimizing human resource turnover,” Applied Intelligence,
2022.
[2] M. Guo, Q. Zhang, X. Liao, F. Y. Chen, D. Zeng, and D. D. Zeng, “A hybrid machine learning framework for
analyzing human decision-making through learning preferences,” Omega-international Journal of Management
Science, 2020.

You might also like