HR Analytics: Workforce Optimization with Machine Learning

Predicting employee turnover, performance, and promotion eligibility using Random Forest, XGBoost, and LightGBM

Created by: Christ Raharja
Ex Technology Risk Consultant, and E-commerce enthusiast

What Will I Learn?

• Learn how to build employee turnover predictive model using Random Forest
• Learn how to build employee performance predictive model using XGBoost
• Learn how to build promotion eligibility predictive model using LightGBM
• Learn how to analyze the impact of overtime work on turnover rate
• Learn how to analyze the relationship between work life balance and turnover rate
• Learn how to analyze the relationship between number of promotions and turnover rate
• Learn how to analyze the relationship between education level and employee performance
• Learn how to analyze the impact of remote work on employee performance
• Learn how to identify top performers in the company
• Learn the basic fundamentals of human resources analytics, technical challenges and limitations in HR analytics, and its use cases
• Learn how HR predictive modeling works. This section covers data collection, preprocessing, feature selection, train test split, model selection, model training
• Learn about factors that contribute to an employee's performance and turnover rate, such as job satisfaction, work life balance, compensation and benefits
• Learn how to find and download HR dataset from Kaggle
• Learn how to clean dataset by removing missing values and duplicates
• Learn how to handle imbalanced dataset using Synthetic Minority Oversampling Technique and Adaptive Synthetic Sampling Approach
• Learn how to evaluate the accuracy and performance of the model by calculating precision score, recall score, and creating confusion matrix

Requirements

• No previous experience in HR analytics is required
• Basic knowledge in Python and machine learning

Target audience

• People who are interested in gaining valuable insights from HR analytics
• People who are interested in building HR predictive models using maching learning