Finding a Clear Voice in IVR

By Tal Cohen, Ph.D.

When was the last time this happened to you? You have a problem or question, so you decide to call the company. An automated system responds to your call. You roll your eyes, listen to the menu, don’t hear an option that applies to you, and end up pressing zero to speak to an agent. Another automated voice tells you that your wait may be long, the hold music trills away and you wonder if any human actually works for the company.

As organizations become larger and more complex, providing that “personal connection” with callers becomes more and more challenging. Serving callers well, however, is a requirement to remain competitive. To handle the rapidly growing volumes of customer interactions, many call centers turn to automation. They build elaborate websites while expanding the duties of what is often looked down upon in the customer service family, the dreaded interactive voice response system, or IVR.

The phone continues to act as an important avenue for self service. Gartner reports that 92 percent of customer interactions happen over the phone – a statistic that makes a strong case for more effective phone communication. Despite the fact that organizations are pushing people to self-serve over the Web, global cell phone subscriber growth is outpacing Internet user growth and customers are three times more likely to call a toll-free number than use a self-service Web application.

The vast majority of phone interactions begin in some type of automated application, which is deployed with the goal of enabling customers with low to medium complexity questions or needs to serve themselves. These systems almost always include DTMF, or touch-tone IVRs, and many companies are also deploying speech recognition technologies in their automated offerings as well. Having a complete understanding of callers’ experiences in these automated applications is imperative – as they act as a “welcome mat” to the majority of customer experiences.

The problem is that IVR systems are often deployed with very clear business objectives in mind, but user goals are much more difficult to identify. These applications can save money. According to Forrester Research, the average cost of a live customer service agent phone call ranges from $5 to $15, compared to self-service interactions that typically cost less than a dollar per transaction.

In order to interpret user objectives, most IVR applications rely on high-level volumetric data, anecdotal evidence, or incomplete user surveys for improvement answers. This results in systems that are poorly designed and subsequently do not meet user goals. The ability to monitor and measure actual user behavior in IVR and speech-enabled applications enables identification and improvement of problem areas that cause user drop-off or confusion and additionally define areas where automation can be extended to better serve callers.

Given the potential cost savings, organizations are striving to create effective IVR systems that allow organizations to automate a wide variety of complex customer interaction tasks at a much lower cost than agent-handled transactions. Despite these advantages, the potential of IVR systems as an effective customer service tool has been largely untapped.

In order to optimize any system, organizations must identify how they are going to measure the success of the system. Self service applications such as IVRs are no different in this regard. If cost-reduction is one of the system objectives, then measuring how successful the system is in containing and self-serving callers inside the system – and avoiding a live agent phone call – should be one of the measures. Many IVR applications not only do not meet user goals, but also fail to deliver the expected cost reductions due to sub-optimal design.

Why? Because today, many IVR systems are modified on gut feelings, subjective guesses, or anecdotal, random information about what callers want – not with hard data about the users’ behavior and desires.  Then call centers spend millions of dollars on new technology to improve the IVR system, such as speech recognition, in an attempt to “fix” the problem. However, the root cause is still unresolved. Since companies do not have a way of factoring in actual users’ behavior systematically, the new technology falls short of its potential just as its predecessor did.

The best way to align business benefits with user objectives is by focusing on user behavior – understanding how customers are acting once inside the IVR/Speech system and subsequently incorporating that insight with existing caller and transactional information. Using this knowledge to drive user-behavior based IVR/Speech improvements can significantly enhance an organization’s customer-facing solutions.

Customer behavior intelligence technology can help call centers monitor and measure user actions in interactive systems, including speech recognition applications. The technology can improve the effectiveness, speed the time-to-benefit, and increase the associated return on investment for speech deployments. Customer behavior intelligence can be deployed on current DTMF IVRs before speech applications are implemented. That way, managers can look at existing systems and get an understanding of current behavior and identify areas where deployment of speech applications would be most effective.

Customer behavior intelligence provides call centers with a map of how, in aggregate, callers navigate through an IVR or speech application. The map will show deviations from the expected flow and the implications of these deviations. For example, if callers continue to get caught in an ambiguous state, rather than efficiently moving through the application, this deviation and its’ impacts will be clearly understood with customer behavior intelligence. As an organization gains insight into an IVR system’s success, it can effectively measure caller behavior, analyze user behavior measurements, and decide on and implement changes.

In a 2005 Forrester study of 15 large IVR systems in airline, credit card, and wireless industries, just one IVR received a passing grade in terms of value, navigation, presentation, and their ability to engender trust and repeat usage. What factors can explain such widespread failure? These companies have invested millions of dollars in designing and building these systems – a critical element must be missing. With behavioral insight, call centers can better balance and meet service objectives. The key to optimizing business performance is to turn meaningful observation and analysis into new, value-driving action.

Dr. Cohen holds a Ph.D. in Mechanical Engineering and a Master of Science degree in Computer Science. He is president, CEO, and co-founder of ClickFox.

[From Connection Magazine June 2005]

One thought on “Finding a Clear Voice in IVR

  1. Pingback: The June 2005 Issue of Connections Magazine | Connections Magazine

Leave a Reply