The increasing challenge of employee attrition poses a significant concern for organizations, impacting workforce stability and overall performance. The Analysis of HR Data to Predict and Understand Employee Attrition problem centers on the utilization of data analytics and machine learning techniques to assess and anticipate employee turnover within an organization. By examining historical human resources data encompassing factors like employee demographics, job roles, performance metrics, and engagement levels, the objective of Employee-Attrition-Armor is to construct a predictive model that can identify patterns and indicators contributing to employee attrition.
Employee AttritionArmor is a data-driven, machine learning project that generates valuable insights and predicts the attrition of employees in an organization.
The dataset used in the project contains 35 attributes and over 1400 records. It is explored and cleaned to get rid of any redundant and null values.
Feature Selection and Engineering is performed to remove the unnecessary attributes in the data. The categorical data is converted into numerical data for easier analysis.
By identifying patterns and key indicators with the help of correlation matrix which contribute to attrition, the project seeks to equip organizations with actionable insights.
Three different machine learning algorithms are used in the project to determine the best suitable algorithm which provides better accuracy and performance among them.
Machine Learning Algorithms: Support Vector Machine, Random Forest Classification, Gaussian Naïve Bayes
Libraries Used: Pandas, Matplotlib, Numpy, Scikit-learn, Seaborn, OneHotEncoder
Language Used: Python
Platform Used: Google Colaboratory
Dataset: IBM HR Employee Attrition