Go Back

The quitting algorithm will tell you who are at risk

Nov 17, 2019 6:00:00 PM / by Anna

But it’s still your job to retain your key talents

The masterminds behind the quitting algorithm, professors Brooks Holtom of Georgetown University and David Allen of Texas Christian University, used big data and machine learning to identify the employees who are most likely to quit.

The algorithm is shaped around two main indicators: “turnover shocks” and “job embeddedness”: the former is measured in events that may prompt employees to quit the job, for example, legal actions against the company, scandals, change of management or change in personal circumstances such as the birth of a child. The “job embeddedness” describes how deeply connected an employee feels to the company and is based on the publicly available data. Indeed, the people classified as “most likely” to be receptive to new opportunities were 63% more likely to change jobs within the three-month period. 

While the algorithm does the heavy lifting on the data analysis, it’s up to managers how to put this data to work. “Even if you can predict who’s leaving, it still requires you to respond thoughtfully,” says Brooks Holtom. Nevertheless, the data is an essential starting point to develop listening culture within the company and learn more about what employees really value. Armed with this knowledge, managers can reduce the risk of losing their top talent before important events and in general build a happier work environment. 

Source: This algorithm can predict when workers are about to quit—here’s how

 

Tags: Employee Retention, Attrition

Written by Anna