It is said that one of the most valuable assets for companies is human capital. In a moment of recovery of markets and employment, companies are challenged to capture talent but also to know how to retain it and motivate it.
The reasons for leaving a job can be many and vary according to different factors such as age, profession, country, etc. In order to avoid highly talented individuals quit their jobs, many companies spend a great amount of time and also money investigating the causes of employee turnover.
The project will be addressed to analize and understand in detail:
I have always been interested in themes related to human relations so, I have done my best to be able to address it in this project. Although it has not been easy to find HR information the truth is that I feel confortable with the dataset and also very excited.
To understand the information included in the dataset and be sure that I am working with cleaned data — data that is organized, complete, recent, and generally high quality.
- Programming languaje: Python
- Programming languaje: R Markdown.
The result has been published in the following link: RPubs publication.
The aim is to segregate groups with similar traits and assign them into clusters based on feature similarity. I will use k-means clustering. The graph/image resulted of the anaysis has been keeped into "img" folder.
- Programming languaje: R
Using classification or clustering methods in HR, companies can work on target areas or departments, even segment employees based on performance, evaluations or satisfaction level monitoring, avoiding possible future "brain drain".
Using machine learning tools, I will try to predict whether the employee will leave the company or not indicating which is the best model to get it.
- Programming languaje: Python
Please note that the conclusions of the analysis have been included into each corresponding notebook/file.
This work was done with great effort and affection. I really hope you like it and enjoy it.