https://github.com/waizkhan7/waizkhan7-deep-analysis-of-hr-employee-data-using-data-mining-techniques

https://github.com/waizkhan7/waizkhan7-deep-analysis-of-hr-employee-data-using-data-mining-techniques

Last synced: 7 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/waizkhan7/waizkhan7-deep-analysis-of-hr-employee-data-using-data-mining-techniques
• Owner: WaizKhan7
• Created: 2020-10-21T21:06:15.000Z (about 4 years ago)
• Default Branch: main
• Last Pushed: 2020-10-21T22:05:14.000Z (about 4 years ago)
• Last Synced: 2023-07-19T11:28:37.447Z (over 1 year ago)
• Language: Jupyter Notebook
• Size: 2.64 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# WaizKhan7-Deep-Analysis-of-HR-Employee-Data-Using-Data-Mining-Techniques

The analysis of HR Employee Data, consists of following steps:

Initial Analysis,\

Chi Square Analysis,\

Clustering and Outlier Analysis,\

Conclusion and Recommendations.

**Initial Analysis:**

In this part, first it was first checked, if there is any empty/null entries in the data. Then categorical attributes were converted into numbers to view the data.

After that, data was divided into two groups, data of employees who left the company and who stayed. The mean of different attributes were compared, to check which attribute differ greatly among both groups.

**Chi Square Analysis:**

Chi Square Analysis was performed on categorical attributes to check, how much change in both groups of employee occured when they were divided in those categories. Like, did that categorical attribute made any difference, with the help of null hypothesis.

**Clustering and Outlier Analysis:**

Data was clustered using different techniques like **Kmeans clustering**, **BIRCH** and **Agglomerative clustering**. To find the **optimal number of clusters** of the data, **elbow method, visualisation method and Dendogram** were used.\

Later, outliers were removed using **Isolation Forest**, since it worked best on multiple attributes/dimensional data.

**Conclusion and Recommendations:**

After the detailed and deep analysis of the data, with the backing of results of all the analysis and techniques, few recommendations were made on how more employees can be retained by the company. And also what factors were behind employees retention and leaving of the company.

**Note:**

The report of the all the analysis described above and their code is shared in the repository.