From the course: Data-Driven HR: AI-Powered People Analytics for Workforce Planning and Employee Experience

Unlock the full course today

Join today to access over 24,700 courses taught by industry experts.

How to predict employee attrition

How to predict employee attrition

From the course: Data-Driven HR: AI-Powered People Analytics for Workforce Planning and Employee Experience

Start my 1-month free trial Buy for my team

How to predict employee attrition

“

- When building your attrition model, one factor you'll want to decide with a business is the intervention window. How much lead time realistically do we need to prevent someone from leaving if the model predicts they're at risk? It's likely not three days, but a year is likely too long because a lot can change. If you set up the model to predict people who are at risk of leaving in the next 365 days, there's a lot that can happen in a window. So, generally, I've seen 30 days to six months In practice. There are two types of machine learning models, supervised and unsupervised. In the supervised case, you provide a computer with labeled data, telling it what each piece of information means. For example, you could train a model to predict whether a customer will renew their Amazon Prime subscription based on their past behavior and preferences. On the other hand, with unsupervised learning, the computer is given a lot of data and looks for patterns and relationships on its own. This is…

Contents