Predict employee attrition and explain what drives it

You get an HR dataset with one row per employee (age, job role, monthly income, overtime and similar columns) and a label saying whether the person left. Build a model that predicts attrition and use it to explain which factors drive people to leave. Cover cleaning and encoding, the class imbalance, your choice of model and metric, validation, and how you would present the drivers to non-technical stakeholders without overstating causation.