Data Science Can Help Companies Hire the Right Call Center Agents and Drastically Reduce Turnover
It’s conventional wisdom that the nature of contact centers leads to high turnover. Call center jobs don’t often offer very high pay, and the work itself often turns people off. Contact center work is often considered by many to be a “patch” to tie one over between jobs, or help pay the bills on a part-time basis. For all these reasons and more, the average turnover in the average contact center tends to be high.
This costs companies a lot of money. Recruiting and hiring take time and cash, and training a call center agent is an extensive process that often takes weeks. To fully train a new agent, only to have that person leave, is a waste of resources.
Still, most companies have a few agents who are very good at their jobs – even like their jobs – and stick around for the long term in order to work their way up the ladder to supervisor and even management positions.
So how do you identify the latter type of people and hire more of them?
Some companies are turning to data science to figure it out, according to a recent blog post at the Web site Data Informed.
“Data science has a long and mature history of measuring the human attributes of consumers to predict advertising responses, upsell patterns and other purchasing patterns,” writes blogger Pasha Roberts, chief scientist at Talent Analytics Corp. “Employees are equally human, and have even more impact on the success or failure of a venture – making it worthwhile to use a data science approach here as well, to model and optimize teams and companies.”
Roberts notes that the underlying concept with this approach is the assumption that people have personal, intrinsic attributes that are different from skills and training that can be either strengths or weaknesses in different roles, particularly in relation to call center jobs. Call it, perhaps, “raw talent” or aptitude; finding its nature and isolating it can make a huge difference in hiring.
Some of the factors the data science approach measures include a person’s level of curiosity, problem solving approach, degree of cooperation, aggression, service orientation, and a focus on results. Depending on the nature of the call center’s business, the requirements for a “perfect agent” may vary. If the agents are selling competitively, for example, a competitive personality might be desirable. If a team approach is required, however, a competitive personality would not be desirable.
It’s not the kind of thing that can be done slapdash or by amateur dabblers, according to the Data Informed article.
“These models cannot be built by anecdotal, subjective judgments,” he writes. “It is too complex for the human brain to process fairly and consistently. To eliminate bias, modern data science methods need to be used to gather samples, then build, evaluate, and implement talent models.”
It’s certainly a task for professionals, and it’s likely not an inexpensive process. Given how much constant turnover costs the average contact center, however, and it just might be worth every penny.
Edited by Blaise McNamee