/HR_Dataset_Exploratory_Data_Analysis

In this repository i started with an EDA for a randomly created HR-related dataset from kaggle. If there is some more time, I'll try to go on with creating a model to predict the performance or salary.

Primary LanguageJupyter Notebook

Image Source

HR Analytics

HR departments have a tradition of collecting vast amounts of HR data. Unfortunately, this data often remains unused. As soon as organizations start to analyze their people problems by using their data, they are engaged in HR analytics. Over the past years, Human Resource Management has changed a lot. It has moved from an operational discipline towards a more strategic discipline.

HR Analytics enables HR professionals to make data-driven decisions and it helps us with interpreting organizational data. It helps to find people-related trends in the data and helps the HR Department taking appropriate steps to keep the organization running smoothly and profitably.

Questions coming up for that dataset might be:

  • What is the overall diversity profile of the organization?
  • What are our best recruiting sources if we want to ensure a diverse organization?
  • Are there areas of the company where pay is not equitable?
  • How high is your annual employee turnover?
  • What characterizes our most successful managers?

And further more ...

Dataset

The dataset is is a randomly created HR-related dataset from kaggle: https://www.kaggle.com/rhuebner/human-resources-data-set The CSV revolves around a fictitious company and the core data set contains names, DOBs, age, gender, marital status, date of hire, reasons for termination, department, whether they are active or terminated, position title, pay rate, manager name, abscences, most recent performance review date, employee engagement score and performance score.

At this point I would like to mention: In this dataset there are some features like race. In the United States it is common that various groups are categorized according to the United States Census Bureau. Even though I don't agree with this feature in this fictional dataset it's just an example to analyze the diversity of a company.

EDA

Here you can find the notebook for some insight on my EDA.

And here you can find the final presentation with all results.

I know there is some future work and I'll try to go on as soon as possible. But at this stage the EDA can show some ways to gain insights from your HR Data.