Next Article in Journal
A Novel Method for Survival Prediction of Hepatocellular Carcinoma Using Feature-Selection Techniques
Previous Article in Journal
Scene Text Detection Using Attention with Depthwise Separable Convolutions
 
 
Article
Peer-Review Record

Predicting Employee Attrition Using Machine Learning Approaches

Appl. Sci. 2022, 12(13), 6424; https://doi.org/10.3390/app12136424
by Ali Raza 1, Kashif Munir 2,*, Mubarak Almutairi 3,*, Faizan Younas 1 and Mian Muhammad Sadiq Fareed 1
Reviewer 1:
Appl. Sci. 2022, 12(13), 6424; https://doi.org/10.3390/app12136424
Submission received: 12 May 2022 / Revised: 6 June 2022 / Accepted: 15 June 2022 / Published: 24 June 2022

Round 1

Reviewer 1 Report

The authors use four machine learning methods to predict employee Attrition, and analyze the important factors that lead to employee Attrition, the results show that the proposed Extra Trees Classifier prediction method outperforms recent studies.

 

Here are some suggestions:

 

1. The innovation of this paper is not clear, the author can emphasize it in the introduction.

 

2. Suggest an increase in the literature review on employee Attrition rates, and suggest that authors comment on cited papers, point out the deficiencies of existing methods for the problems they face, and then explain the performance of these previous studies? Are there significant differences between the proposed method and other methods?

 

3. It is suggested that the authors provide some discussion results in the conclusion section, and can comment on the main factors of employee turnover in the results of their analysis. or can there be more description of the future development direction or guidance?

Author Response

Please see the attachment

Author Response File: Author Response.docx

Reviewer 2 Report

The paper is about the use of machine learning techniques for the prediction of employee attrition.

I think the article should be improved in some aspects in order to be considered for publication. Firstly in the related works should be analyzed balancing techniques and comment on some techniques of neural networks.

For example, why the use of SMOTE and not another balancing algorithm or some other technique that is more robust to balancing.

On the other hand, explain why the proposed techniques have been selected and not used techniques such as deep neural networks or xgboost which are quite robust to unbalancing.

 

Finally, being unbalanced ensembles, I think it would be interesting to use some more metrics such as G-Mean.

Author Response

Please see the attachment

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report

Previous comments and concerns have been fully addressed, Several improvements have been added to the revised document.

Reviewer 2 Report

The authors have answered my questions, I recommend publishing the article in the current version.

Back to TopTop