Analytics stops customer issues before they happen

Register now

Predictive analytics has already proven to be a tool for preventing mechanical or software issues before they even happen. Can this be applied to people as well?

Of course. This is happening at CSS Insurance, as recently explained by Volker Schmidt, CMO and CIO for CSS Insurance. (Wow, he’s a busy guy!) In a recent video posted by Teradata, Schmidt explains how CSS is using big data as marketing analytics to enhance customer satisfaction. For starters, no company could last long these days without intelligently applying data analytics. “If you’re talking about customer satisfaction without using data, you have no facts, and it’s really difficult to convince colleagues you have to invest in customer satisfaction. With data, it’s quite clear how we stand.”

That’s because data and analytics provides transparency “in every single customer interaction, billing, call center, claims, website,” Schmidt states. “If a customer has any contact with CSS -- if he wants to change his address, for example -- the call center agent will put the service request, and it goes back to the data warehouse. From there it’s generated automatically a lead to another call center to ask the customer. If he is not really satisfied with the service, we send out another lead client rep to solve this problem immediately.”

Importantly, the smart application of data analytics may help prevent customer service issues before they happen. While predictive analytics is being successfully applied to forestall mechanical or software issues, Paul Berger and Bruce Weinberg, writing in Harvard Business Review, see the potential to predict and address customer issues before they even become issues, as well. Interventions can be planned accordingly.

At CSS, data enables fast sentiment analysis on various customer communications, helping the insurer to steer customers toward more cost-effective medical treatments. “We are still at the point to understand how our clients are behaving, according to the claims processed,” says Schmidt. “Why do they go to these doctors, why do they go to these specialists, why do they go to these hospitals.” With that information, CSS can provide relevant research on providers for its customers. “It’s not up to insurers to say ‘hey, that’s not the best therapy for you.’ What we are trying to do with this information is make the information transparent on our website: that the customer sees what kind of provider is the best for his treatment.”

This is where predictive data analytics on customer patterns will demonstrate its ultimate business value – when and where to apply interventions, Berger and Weinberg write. They discussed how one client – who sold mobile phones -- employed “a predictive model to rank-order each customer over a given period of time from high to low probability that a member is a ‘returner’ (without an intervention).” Those in the top 10% in terms of likelihood to return accounted for 40% of all returns. Thus, targeting that top 10% in a preventive way would help reduce 40% of returns.

“There are many marketing and business problems where customers take undesirable actions that can negatively impact organizations and providers,” says Berger and Weinberg. “Fortunately, marketers can effectively disrupt these actions with an intervention. Optimizing, at least for a given intervention, is now being recognized as a useful implementation in many situations. We wouldn’t be surprised if the term “intervention analytics” becomes a well-known phrase, given the mushrooming of the field of marketing analytics, and the potential upside for companies.”

For reprint and licensing requests for this article, click here.
Customer service Customer experience Analytics Predictive analytics People analytics Machine learning