Visier’s Predictive Analytics Technology Found to Be up to 8x More Accurate at Identifying “Resignation Risk” Employees

Share Article

Assessment validates Visier’s patented Continuous Machine Learning approach.

Visier technology performs a unique clustering analysis to generate a Key Drivers analysis.

Visier’s Continuous Machine Learning approach to predictive analytics continuously analyzes all potential reasons for turnover.

Visier, the innovation leader in Workforce Intelligence, today shared the results of an in-depth validation of its patented predictive analytics technology. The assessment found that Visier is up to 8x more accurate at predicting who will resign over the next three months than guesswork or intuition -- and up to 10x more accurate when focused on the top 100 “at risk” employees at a given organization.

“There has been significant hype around predictive workforce analytics, specifically around identifying employees most at risk of exiting an organization,” explains Dave Weisbeck, Chief Strategy Officer, Visier. “The problem is that most ‘at risk’ predictive analytics capabilities available today are too narrowly applied and are in their infancy -- they have simply not been used for long enough by enough companies for enough employees on enough sources of data. Visier’s algorithm, on the other hand, has been making predictions for years, which has given us years of history across multiple customers and industries, and tens of thousand of exit events. The result is an unprecedented ability to validate how accurate the predictions are.”

Read the blog post to learn more about Visier’s technology and how the accuracy of its predictions was validated.

Continuous Machine Learning

Visier applies a Continuous Machine Learning approach. For each customer, Visier’s patented in-memory multidimensional analytics technology looks back over 18 months, at all employees and potentially hundreds of employee variables or attributes, as well as the groupings within each attribute, and determines how much each correlates to the employee resignations that have occurred during that period. Visier then automatically assigns each current employee an “at risk” score, essentially ranking each employee from highest to lowest in resignation risk.

All of this is calculated dynamically and instantly, so when an HR analyst, business partner, or leader goes into Visier and asks which employees are “at risk” in a specific employee sub-group (for instance, specifying a role, location, tenure, and performance level), Visier automatically provides the relevant results, based on the latest, most current data applicable to the user.

Visier does not artificially limit or restrict what data is analyzed. Rather, Visier always considers all the attributes for the group of employees being looked at. Because Visier analyzes all employee data (from all systems holding employee data), Visier is not limited like HR Management applications, which manage only a portion of the employee lifecycle.

A typical approach by many “at risk” predictors is to perform a regression analysis on a select group of attributes. For instance, a manager thinks salary and tenure have something to do with resignations, so the analyst looks for a correlation between those attributes and resignations to see if the manager is right. They may indeed prove to be right, but in artificially limiting the analysis, several other attributes that relate to resignations may be missed.

More sophisticated methods train algorithms with various machine learning techniques. However, these methods are also limited: people leave companies for a variety of often surprising reasons and those reasons change over time.

“For the best results,” Weisbeck says, “all potential reasons -- in the form of all employee attributes, across all HR systems -- should be considered, and the results should be calculated continuously to take into account changing conditions. Hence, Visier’s Continuous Machine Learning approach.”

HR’s Critical Role

Despite the hype and Visier’s great results, predictive analytics will not replace human intervention: predictive analytics is about more than who will leave, it is about why they are leaving.

Visier technology performs a unique clustering analysis to generate a Key Drivers analysis, which shows which of the hundreds of employee attributes are most related to an increase or decrease in resignations.

“This sort of prediction is even more valuable than naming individuals,” says Weisbeck. “Identifying the key drivers of resignations allows HR to develop thoughtful, refined, long-term programs to reduce resignation rates by targeting root causes.”

About Visier

A leading innovator in Applied Big Data cloud technology, Visier provides Workforce Intelligence solutions that are enabling a rapidly growing number of the world’s best brands to maximize their business outcomes through their people.

Visier’s solutions let organizations understand and plan -- with precision -- how to best and most cost-effectively recruit, retain, and develop their workforce. With Visier, senior leaders, HR, and people managers alike can answer key workforce questions, align on goals and strategies, and act on decisions and plans to drive improved business outcomes. Visier does this by providing complete pre-built solutions in the cloud as a service that leverage Visier’s innovative multi-dimensional, in memory technology to provide capabilities otherwise not possible.

Founded by business intelligence experts—including former Business Objects chief executive officer, John Schwarz—the company's leadership team has a proven track record of technical, operational, and strategic management success with companies such as IBM, SAP, and Oracle. With millions of customer employee records in the cloud, Visier is experiencing significant growth.

For more information, visit http://www.visier.com.

Media Contact:
Brittany Bevacqua
Affect
212.398.9680
bbevacqua(at)affect(dot)com

Share article on social media or email:

View article via:

Pdf Print

Contact Author

Brittany Bevacqua
Affect
+1 (347) 491-5959
Email >
Visit website