Skip to content

Latest commit

 

History

History
58 lines (37 loc) · 2.13 KB

churnAnalysis README.md

File metadata and controls

58 lines (37 loc) · 2.13 KB

Churn Analysis on HR_comma_sep.csv file

author: Kuuku Baffoe

OBJECTIVE:

.To identify some the leading causes of employee churn from solicited feedback to enable HR develop long-term strategies to reduce it.

INSTALLATION

.In order for the code to operate properly, the following modules must be downloaded. .Pandas: Pandas makes it straightforward to perform many of the time-consuming, repetitive operations involved with data processing .matplotlib: Matplotlib is a data visualization and graphical charting package for Python and its numerical extension NumPy that is cross-platform. As such, it provides an open source alternative to MATLAB. .seaborn: Seaborn is a Python module for creating statistical visuals. .sklearn: It offers a set of fast tools for machine learning and statistical modeling, such as classification, regression, clustering, and dimensionality reduction, via a Python interface.

csv file can be downloaded here: https://github.com/RuchitaGarde/Human-Resources-Analytics/blob/master/HR_comma_sep.csv

USAGE

Run code with csv file in python ide of choice.

OBSERVATIONS

.According to the scatter plot of satisfaction level to last evaluation, a higher percentage of those with higher scores in their last evaluations were the most satisfied, while a significant number of employees with low evaluations had lower satisfaction levels. this might indicate a tensed / competitive environment.

.Those with four projects were the most happy, while those with more than four were less content. This might suggest that some employees felt overworked.

RECOMMENDATIONs

.introduction of team bonding activities like retreats etc to reduce tension

.A more equitable workload distribution across employees would boost employee satisfaction.

CONCLUSION

Accuracy: 0.9715555555555555 Precision: 0.958252427184466 Recall: 0.9207089552238806

According to the various data visualized, the number of projects, average monthly hours, and last evaluations were the key factors of satisfaction level, which in turn impacted staff attrition.