Most of the work we do in the field of people analytics is oriented to helping organizations understand what is most important to their employees, with the goal of making improvements to increase employee engagement and productivity, and reduce unwanted attrition.

Employee attrition analytics is specifically focused on identifying why employees voluntarily leave, what might have prevented them from leaving, and how we can use data to predict attrition risk. Most importantly, this type of employee predictive analytics can be used to help organizations understand and design the interventions that will be most effective in reducing unwanted attrition.

Although we have moved within the past month from an environment of historically tight global labor markets to one of widespread unemployment due to the COVID-19 pandemic, employee attrition analytics will remain important to organizations seeking to retain top talent; even in times of high unemployment, top performers are always in demand and there is competition for their talents. Predictive analytics capability enables the design of an employee retention model to keep these valuable employees engaged and on board.

In this article, we’ll examine how organizations can use predictive analytics to impact employee attrition and retention—and prevent the loss of hard-to-replace top talent.

Employee Attrition And Retention: Striking The Right Balance

There are actually two types of attrition problems: too little, and too much.

When considering attrition, many leaders tend to focus on the problem of high turnover—with good reason. Recruiting, hiring, onboarding, and training new employees costs businesses billions each year. Companies also suffer productivity losses—and lost profits—when there is a large amount of continuous churn in the workforce. Top talent, in particular, can be very difficult and expensive to replace. Financial considerations aside, businesses are better off when they can retain good employees and the organizational knowledge they possess.

But too little attrition can also be a problem. The right amount of attrition—with the right people turning over at the right time—is desirable. Not every organization or every job is right for every person; if an employee who isn’t the right fit or a low-performing employee leaves, there’s an opportunity to fill the role with a high performer who is a better fit for the job. Even if a good employee leaves as a result of “graduating” into a job with a client, if they become a great ambassador for the company, it can be a positive loss.

There may also be positions within the organization that are transitional roles where employees are anticipated to have only a short tenure before they graduate internally or externally to another position. For employees in these types of roles, the goal may not be to keep them in that role indefinitely, but to keep them in those positions for just a few months longer, to reduce turnover costs and disruption.

The goal with employee attrition and retention is to strike the right balance of holding on to top talent while accepting that some level of attrition is healthy; employee attrition analytics enables organizations to find that balance.

Learn more about how you can improve the culture in your company - and help your people thrive with our free Employee Experience Playbook.

Employee Attrition Analytics: Answering The Who, When, & Why Of Employee Turnover

The first step to building an employee retention model is to determine who is leaving the organization, when they are leaving, and why they are leaving.

To predict future patterns, we first look to the past to answer the who, when, and why questions. As we noted in a previous article, we can find the answers to these questions by using engagement survey data collected six months to one year in the past, and creating a post-hoc demographic of employees who left the organization voluntarily. Analyzing this demographic will reveal information about turnover in various job roles, tenure levels, business units, and locations—and reveal pockets of high turnover—to tell us who is leaving and when.

An employee listening perspective will answer the question of why. We can look at what employees who left were telling us about the workplace, work relationships, and their sense of connection to the organization in the months before they left. The comparison of engagement survey data to termination data can reveal areas of the employee experience in need of improvement. We can also look at how the responses of employees who left the organization varied from those who stayed to see which factors in the experience might have been barriers to engagement. This method can be used by any organization that conducts engagement surveys and has the ability to group employees by various demographic factors.

Exit surveys are another potential data source that can provide richer information. Comparing responses on exit surveys to employees’ engagement survey responses can reveal how the employees’ perceptions changed over time. Correlating exit and engagement survey data can yield additional capability to predict attrition risk.

Answering the who, what, and why questions—and combing the data to see other similarities and differences between employees who stayed versus those who left—is the foundation of employee attrition analytics. An effective employee retention model must be built on the solid footing of the data; otherwise, actions intended to impact attrition are at best only guessing at how to solve the problem—and may be guessing at where the problem actually lies.

Building A Custom Employee Retention Model

Because each organization has its own ideal balance between employee attrition and retention, an effective employee retention model will be unique to the organization and focus on its biggest challenges. And because different employees have different reasons for leaving, the organization needs to be creative and flexible in the actions it takes to retain hard-to-replace talent or extend the tenure of employees in transitional positions.

Some attrition is predictable even without analyzing survey data. If 20% of the managers in an organization will reach retirement age in five years, the organization can start identifying employees who are good candidates for management and get them into the training pipeline; incentives to keep older employees on board after they reach retirement age might also be considered.

However, the analysis of engagement and exit survey data together reveals the less obvious red flags for attrition. Analysis of demographic data alone can highlight attrition hotspots linked to specific job types, work locations, and tenure levels; analysis of the survey data will reveal the reasons why turnover is higher in those hotspots. We can look at the areas of the experience that were failing employees who left according to engagement survey responses, and the reasons employees gave for leaving on exit surveys, and load all that information into the system to inform the model.

As discussed in this previous article, the data analysis can be used to establish internal employee turnover benchmarks. Tracking these benchmarks over time can reveal how the employee experience is changing for better or worse, if the reasons employees are leaving have changed, or if the attrition pattern or time cycle is different. These benchmarks will illustrate whether the actions the organization is taking to reduce attrition are effective, alerting leaders and managers to make adjustments or take different targeted actions if needed.

Managing Attrition & Retention Through Focused Intervention

In some cases, there may be factors that drive attrition across the entire organization. For example, a quickly growing company might lose employees at all levels and locations if work/life balance is an issue. But more commonly, an organization will have higher rates of attrition in certain jobs or at certain points in the employee’s tenure. Because resources are always limited, for many organizations it makes sense to put the most focus on attrition hotspots that affect critical job roles.

Cross-referencing the organization’s demographic and engagement survey data reveals the specific drivers of attrition for each job type, length of tenure, and location—in addition to identifying attrition hotspots. The specific actions needed to reduce attrition in each of those hotspots will depend on what is driving people to leave that particular job or location.

It may be that, in transitional jobs, the organization sees employees burning out before 90 days; that may be an indication their expectations for the job didn’t match the reality. While there’s no expectation that employees will stay in those positions forever, we know that if they make it past the 90-day mark, they are likely to stay for one to two years.

Interventions might include ensuring that interviewers are accurately explaining the job when hiring, or making changes in onboarding to improve the employee’s early experience, making them more likely to stay. Comparing the tenure length of employees who go through the new onboarding process with that of employees who went through the previous iteration will reveal if the new process is making a difference. Has it slowed the rate of churn? Are employees who participated in the new process staying longer? The organization can use this information to make an objective assessment regarding the costs of additional onboarding training versus attrition costs, to determine if the new process is providing savings.

As our data has revealed, the quality of the employee/manager relationship is a big predictor of attrition. If engagement and exit survey data show that the manager relationship is an attrition risk, the organization can review manager training levels to determine if managers with more training have lower attrition on their teams. Survey data will also reveal if managers are performing certain tasks important to keeping employees engaged—setting clear performance expectations, providing useful feedback, and recognizing employee accomplishments. What kinds of manager onboarding training and continuing education can the organization provide to help managers learn the skills needed to retain employees?

Performance data can be incorporated into the retention model as well. In some roles, employees either get promoted within a certain period of time, or they reach a dead end and will likely leave the organization. Using predictive analytics, a manager can be alerted, for example, that half of their team is approaching the 18-month mark where employees typically move up or out. The manager can set up one-on-one meetings with those employees to discuss their career goals and help them either move up or move on; this type of open communication may also help keep some of the employees at risk for attrition in their positions longer, so the inevitable attrition doesn’t occur all at once.

A focus on attrition drivers for top talent is particularly important for many organizations. In these cases, there is often more latitude for interventions; employees in these positions often have unique experience, are highly skilled, or are hard to replace for other reasons. If, for example, an organization has noticed a pattern of attrition in these roles where employees are leaving to become caregivers—either for children or elderly relatives—the intervention may be offering a flexible work schedule, the option to work from home, or other changes in the way they work that will allow them to balance caregiving duties with work.

For all of these interventions, the goal is to be proactive and get ahead of attrition before it becomes a problem. Instead of being on a continuous hiring treadmill, the organization can focus on desirable attrition—moving out employees who are not a good fit or are low performers, and replacing them with the right people for the role.

Ultimately, employee attrition analytics can help your organization design an employee retention model that will work even if attrition is not expected to be a big issue in the near future. The model will still help the organization determine if it is experiencing the right kind of attrition. In a low-turnover environment, when the organization doesn’t have the right people in the right roles and isn’t losing the employees that really need to leave, often it will lose top talent because they are the only employees who have the opportunity to go elsewhere. Low performance across the organization may give top performers a push to leave. Because top performers are always in demand, an effective employee retention model is just as important when unemployment is high as it is in a tight labor market. The key to developing this model is predictive analytics. (Tweet this!)

Want to get ahead of employee attrition in your organization?

At Perceptyx, we help companies design listening programs to address their biggest challenges. With custom surveys paired to our people analytics platform and expertise in all aspects of survey design, strategy, and communication, we can guide you in developing a strategy to help your company reduce attrition and retain your most valuable talent. Get in touch to learn more.