Hero Backgroud Elements 2
Reading Time: 5 Min

How Advanced Analytics Solve Employee Churn

April 6, 2020

Blog
Author
Sarah Detzler Sarah Detzler
Dr Sarah Detzler is a passionate and experienced Data Scientist focusing on data driven use cases to generate measurable added value for our customers. Her goal is to help customers rethink their processes and to ML-infuse every aspect of their business.

In most lines of business and across different industries, it's standard nowadays to use advanced analytics to improve business processes. However, in human resources (HR), the potential of collected data to generate insights is often not considered.

In addition, some companies still export their data to Microsoft Excel to calculate their employees' quota. There is a huge opportunity for HR departments to simplify their analytic process by adopting an analytical dashboard that shows important HR key performance indicators in real-time. The wealth and quality of HR data could also be used for more advanced analytics beyond simple reporting that only looks at past events. What about looking into the future and acting proactively on the issues HR is facing?

Let's take a look at the issue of employee churn and how data analytics can help tackle this issue.

Get started today with your free 30-day trial for SAP Analytics Cloud. Sign up now. 

 

The Challenge of Employee Churn

Companies want to prevent their highly skilled employees from leaving the company. Today, many companies rely on their managers intuition to foresee employee churn. However, this method is neither precise or unbiased. Think about how some managers say that their best guess for a high churn probability is an employee's new haircut. A new haircut might indicate that a person is ready for more important changes. However, could we really deduce this from one factor?

By looking at concrete data and analyzing complex patterns, we can better make effective business decisions. There are people who would argue that human behaviour is too complex to be reflected in datasets.  However, I don't favour one approach over the other. I'm suggesting using both subjective information (such as the opinion of a manager) and the analytical and mathematical conclusions from the data to discover new insights.

Consider this when analyzing employee churn:

  • A high churn rate among new hires could indicate that the onboarding process needs to be improved and thus leads to a reflection of the company culture and a change in the treatment of new hires.
  • We could also take a closer look at internal employee turnover and their success rate or make better learning recommendations based on data.
  • Further, data could be used to help reflect on whether we are leveraging the full potential of our most experienced colleagues.

Tackling Churn with Data Analytics—a Use Case

Let's have a look at an example of how this can be achieved.

Last year, HR use cases were quite popular. One of my students, Harun Behroz, wanted to investigate a specific HR use case through analytic research. Although he had no math or statistical background, he began building a simple dashboard for an HR use case. I introduced Harun to Smart Predict within SAP Analytics Cloud, which enables students and colleagues with an affinity for statistics to do their own predictions, even if they aren't familiar with mathematics and algorithms.

He immediately fell in love with the tool as it gave him the opportunity to find new insights in the given data. Harun was now not only able to visualize how many people left this particular HR company in the last year, but he was also able to analyze the statistical separators of these two groups while predicting the churn score for each employee.

This is great, because when we first started working with HR use cases, Harun said that this BI analysis generalizes too much since each human behaves individually; he believed only looking at the statistics of the two groups might not give respect to this individualism. Sure, he argued that there are groups of people that behave similarly, but there are definitely more than two. This was one of the reasons I enjoyed working with him so much, since he always critically questioned everything. Also, with the predictions we made, he of course pointed out that it will not explain and show all influencing factors and all human behaviour.

Let's be honest, sometimes we just randomly make decisions based on factors that are not described in the data. I can't go into details about the influencing factors since they vary a lot, but there was one factor that was quite interesting. We call it the midlife crisis in a company.

A Common HR Factor—the Midlife Crisis

We found a certain point in tenure where the churn rate increased radically and dropped again afterwards. So, it looked like the employees started reflecting, after being a particular number of years with the same company, on whether they wanted to leave or whether they would stay with the company until retirement. My super motivated student was keen on finding influencing factors that described the churn rate even better. Unfortunately, we couldn't get all the data we wanted. In some cases, there were restrictions and in other cases, the data wasn't appropriately collected and stored. Although this is an issue in many projects, it was also a valuable find, since it allows companies to improve the data mining process for future analysis. This also shows that in most data science projects, data collection and model building are iterative processes.

Bottom Line

Overall, in the end, we had two great models and all we needed was a super motivated student, the right tool, help from the HR colleagues with business and process knowledge, and of course data.

So why not get started and make the most out of your HR data?

Learn More