Keep Customers Coming Back: Personalize Your Automated Calls

Are you losing business with an IVR that does not “listen?”

My 18 year old son was making a call to buy concert tickets with his new smartphone not so long ago. He looked up the concert’s web address on the phone, got the toll free number and rather than give the credit card information online and rack up fees on his data plan, he decided to call. Fairly common these days since many voice apps receive more than fifty percent of their calls from a mobile device.

At the start of the call, James had a strong enough cell signal and he navigated the IVR call script fairly easily. After a minute though, the signal weakened and he started to get frustrated with the fact that the IVR was not allowing him enough time to respond. It was bad enough that he has to deal with the degraded audio quality and latency issues, but now the IVR is constantly asking him to repeat himself. He’s a paying customer with valid credit card, ready to make a purchase and about to get even more frustrated as he tries to secure his concert tickets. As the IVR started it custom designed, tiered re-prompting dialogue, he hears only that he needs to keep repeating himself. He starts to think about how Google might find him a better price on a concert ticket from another source.

The call experience James is having is not at all uncommon in today’s retail environment.

More than ever in the past, telephony-based voice applications must address large and very diverse calling populations.

Another time, my Mom recalled how difficult a time she had calling customer service on a prescription refill voice application at her local pharmacy. Having trouble finding their prescription number on the bottle, let alone read it (even after finding the bottle and reading glasses), she obviously started to take more than the allotted time to touch-tone or speak the number in. When the voice user interface designers made an educated guess that 12 seconds and a 3 second inter-digit timeout value would be appropriate at this script level for most callers, they also understood that an elderly person like my Mom may likely be “pushed” to an agent by the IVR—albeit after encountering considerable frustration. A design trade off perhaps—necessary, but with considerable consequences to customer service and satisfaction.

Again, nothing unusual about my Mom’s call experience.

Automated Call Experience

More than ever in the past, telephony-based voice applications must address large and very diverse calling populations. This audience uses a wide variety of personal, mobile and landline-based devices in various modes to access information over the phone.

Additionally, with a significant increase in the life expectancy of older adults projected and an entirely new generation of technology savvy young adults now beginning their consumer lives, the need to address differences in how humans interact and process spoken information has never been greater. Language, Dialect, Age, Culture, Gender, Communications Technologies and other factors impact the effectiveness of voice communication between humans and computers.

Table 1 shows a list of these factors and the consequences they have on the automated call experience.

When a caller engages with a self-service application for the first time, something subtle yet very powerful happens; The majority of callers will decide in the first 1 – 3 dialogue turns whether or not they feel (a) the system will be productive for them and their interests will be best served by extending the time invested thus far in the system or (b) they have wasted enough time already and their interests will be best served by speaking to a live agent.

This “engagement threshold” is a critical aspect to the success or failure of voice self-service applications. Applications that treat all callers as if they were a single “averaged” user will never make the same critical “first impression” as an application that treats each caller as an individual. This has profound implications for repeat callers and new customers alike.

With an adaptive approach, voice self-service systems continuously monitor individual caller behavior during each call and adjust the output responses accordingly. This approach emulates what humans do during conversation as they continually monitor their audience for clues that the message is being received.

Applications that are “Caller Adaptive” and adjust WPM Speaking Rate, Audio Content, Time Allowed for Responses, Nuance, Audio Volume and other caller centric parameters in real time during the call stand a much better chance of making a good first impression and getting the caller past the all important Engagement Threshold.

Improving IVR Effectiveness and Customer Satisfaction

We tried this “tuning-in approach” on a New York-based voice application that handles over 7,000 travel information inquiries per day.

According to the Call Center Manager, the calls frequently come in bursts. Managing the system to efficiently use the IVR ports is critical to prevent customers from getting a busy signal or forcing them to wait for a live customer service representative.

Applications that treat all callers as if they were a single “averaged” user will never make the same critical “first impression” as an application that treats each caller as an individual.

Using the approach cut the clients average IVR call duration from 171 seconds down to 145 seconds. Because the technology directly cut average call duration they were able to drive more calls through the IVR and thus better manage peak call volumes with the existing IVR system.

Beyond the efficiency savings, the technology also helped the client improve customer satisfaction with IVR self-service. They measured an increase of about 2 percent in the number of calls completed by the IVR application using the technology. Other client sites have seen up to a 20% increase in IVR Utilization (IVR turns) with a corresponding drop in caller input error rates with the approach.

ROI for Cross-Industry Applications

Case studies conducted by Interactive Digital show that for sample B2C Retail, Financial, Travel, Medical Insurance and Government applications, analysis using 95% confidence intervals indicated improvements in IVR Utilization of about 17.24-20.44%, a reduction of First-Attempt Caller Input Errors of about 1.02-1.75% (relative reduction ranging from 4.7-8.0%), an increase in Average Handle Rate of about .5-3% and reductions in Average Handle Time of about 6-16% when incorporating adaptive functionality.

With this increased caller interaction, leveraging the benefits of adaptive technology to accommodate today’s diverse calling populations offers several direct and indirect benefits including increased operational efficiencies, reduced operational costs, increased customer satisfaction and a short and verifiable ROI and payback period.