Foot Locker, a well-known retailer of athletic gear and footwear, has announced it will move toward using predictive analysis to hire employees, particularly as they face limited growth in sales and a high turnover rate.

Every year Foot Locker, based in New York, has more than 1.5 million applications for open positions, and more than 3,400 locations throughout the country, showing that the problem for the company isn’t that people don’t want to work for them. Rather, the issue seems to be holding onto these employees once they’re hired.

“We were looking for an increase in performance,” said Alexis Trigo, Foot Locker’s director of store capability. “We wanted an increase in sales per hour. We wanted a positive impact in our customer experience. And we knew that a side effect of that would be that the teams should be staying longer.”

Beginning in 2010 the talent management team of Foot Locker started looking at ways they could improve customer service and those employees who serve as the face of the company. What they decided on was predictive analysis.

The company said the goal of using big data and predictive analysis is to find the individuals, amongst the millions of applications that show a profile in-line with what the company is seeking in retail sales associates.

Foot Locker partnered with tech firm Infor for the undertaking to utilize Talent Science. Talent Science is a cloud-based software system delivering comprehensive data and predictive analysis, and it also paved the way for Foot Locker to streamline how it hires employees.

Talent Science works by asking applications to take an online assessment, and those questions are then compared with a scoring system, which determines how closely a candidate’s behavior would fall in line with what Foot Locker seeks in retail employees.

“We didn’t want just a warm body who was in our store,” said Robert Perkins, Foot Locker’s vice president of talent management. “We wanted someone who had higher sales capabilities.”

The process of Foot Locker’s predictive hiring includes an initial online assessment, which lets store managers determine where applicants fall on a spectrum of categories.

These groups are :

• recommended,
• recommend with qualifications,
• recommended with reservations and
• not recommended.

From this spectrum, candidates are then selected for an interview, and Talent Science provides personalized questions for each interviewee based on their online assessment. There are usually only three to five pointed questions, and then managers can ask three additional questions based on their unique needs, as well as how the candidate answers the central questions.

When moving toward the predictive hiring model company leaders of Foot Locker needed to make a business case for the changes, which was difficult since they had so many applicants vying for jobs. A team looked at metrics that would create the proof of a return on investment. Some of these metrics used to convince Foot Locker executive included sales per hour, retention rate and the experiences of actual customers in stores.

Another point included in the proposal was that the high number of applications received actually necessitated the change as a way to making hiring more efficient. Without a system in place managers were often faced with hiring on factors like convenience.

Wells Fargo’s Story

Wells Fargo launched a similar program several years ago to find employees that would meet not only performance goals, but also people that would be the best fit for their corporate culture.

Since launching the program, it’s been used to screen more than two million employee candidates.

To standardize recruitment Wells turned to Kiran Analytics, which provides customized solutions, and in this case, they geared much of their focus toward developing formulas that would identify the best potential tellers and personal bankers.

Kiran uses the CloudCords Enterprise Talent Analytics Model instead of simply gauging the results of psychometric assessments (which can often be manipulated by people taking the tests). Kiran looks at biometric data which can often be verified, such as: information pertaining to how long candidates have stayed at past jobs.

Wells Fargo assessments use 65 questions, and these were derived from interviewing and working with subject-matter experts from the banking industry in order to determine the factors key to success in the positions. Once the questions were developed, Kiran asked 1,000 current Wells Fargo team members already holding the targeted positions to take the assessments.

Using the results from present bankers and tellers, Kiran extrapolated correlations based on culture and background, which were then incorporated as a means to minimize turnover, balanced with choosing top performers.

How to Use Predictive Analytics

Big data is completely changing the recruitment and talent management world, and it impacts not just how employers secure talent, but also how they retain their top performers. Research firm Gartner predicts big data will grow by a whopping 800 percent over the next five years, and much of that data will be represented by unstructured means, such as emails, social media posts, and resumes.

Some of the ways predictive analytics and big data will be most frequently used include:

• Strong predictive analytics look at not only how businesses can hire the best talent, but also how to best reach these people and what they’re going to find most attractive in a job. These are important issues as companies are facing talent shortages.
• Talent pipeline planning: Not only can you source the talent with the most potential, but you can also build your pipeline planning strategy by looking at a variety of talent data.
• Corporate culture: As mentioned with regard to Wells Fargo, companies are increasingly looking to not only hard skills, but also those soft skills that make someone not just a good technical fit for a position, but a good corporate fit.

Does your company rely on any form of predictive analytics in your talent management strategy? If so, in what ways?

This site uses Akismet to reduce spam. Learn how your comment data is processed.