How to take action with Call Center Analytics

/, Call Center Quality, Customer Experience, Quality Assurance/How to take action with Call Center Analytics

How to take action with Call Center Analytics

Share on LinkedIn7Share on Google+0Tweet about this on TwitterShare on Facebook7Pin on Pinterest0Email this to someone

A large part of the success of any contact center operation is dependent upon people; not technology as you might assume. Those measuring the customer experience and those delivering the customer experience must work in concert to define the specific business need to take action with call center analytics.

NOTE: Is this article advanced for you? If it is, use it as a self-assessment to tell yourself that you must learn more because understanding analytics is becoming a necessity to become a high-performing call center leader.

“Understanding call center analytics is becoming necessity for high-performing leaders.” Click to Tweet

Identify the data available to answer that question and, validate the interpretation of analytic outputs as applied to the business environment. Now from this point, the subject-matter experts, such as statisticians, data analysts, data miners, researchers, etc. focus their skill and body of knowledge to determine the best methodology for the project.

Analytics to do what?

Perhaps you’ve been like the many call center managers who have announced to me “I need a model for call center operations!” Really? What type of model? Logistic? Linear? What kind of data do you have for me? What do we need to predict? What action will you take with the results? And many more questions.

My point is that you do need a model but you probably haven’t asked for the right thing. In an environment where “half of the organizations surveyed do not take advantage of analytics to help them target, service, or interact with customers” according to Accenture’s Customer Analytics survey, predictive models have gained the esteem and notoriety, but only by the half that use them.

Convincing a call center manager, or their manager, that they do not need the model they think they need may be challenging.  Beyond that, below are two runner-ups in the predictive modeling toolkit that professionals charged with improving the customer experience tend to have missing from their toolkit:

Discriminant Analysis – Discriminant analysis is used to determine which variables discriminate or separate into naturally occurring groups. In a call center environment, the goal is to understand what variables discriminate between customers who a) become promoters of the brand, b) become detractors of the brand, or c) remain neutral about the brand. Alternatively, it’s helpful to understand the variables that discriminate between customers who will perceive issue resolution versus those who do not. Was wait time a driver of outcome? Perhaps the number of times they were transferred or placed on hold during the call?

Cluster Analysis – Customer analysis is used to divide populations (in marketing, our populations are typically customers) into groups or clusters so that all customers in a cluster are similar in some (meaningful) way and more importantly, dissimilar from the customers in other clusters. This methodology is useful to help call center organizations better understand the customer experience. A cluster analysis based on call outcome could reveal (prove) that after three transfers, customers lose faith in the interaction and the organization, defecting to the nearest competitor. A different cluster analysis based on product could indicate an issue with the level of knowledge of company-approved servicers / repair professionals.

More than reporting

So, predictive modeling is not simply a reporting activity. It’s much more than that, but you don’t need to become the expert. To be successful, work with a business intelligence analyst to help guide the model building and application of that information. The exciting part about data can be fully realized when the analytics are strong (and correct!). Just because you can get a model out of an Excel spreadsheet, doesn’t mean that you have accomplished what you need to gain a competitive advantage and do more with less.

About Dr. Jodie Monger

Jodie Monger, Ph.D. is the president of Customer Relationship Metrics and a pioneer in voice of the customer research for the contact center industry. Before creating CRMetrics, she was the founding associate director of Purdue University's Center for Customer-Driven Quality.

View All Posts