Gyst CX – personalization software for voice self-service

Gyst CX (customer experience) is a version of Gyst specifically designed for use in self-service voice applications. This patent pending technology is easily implemented in both hosted and on-premise interactive voice response (IVR) systems via a simple to use web or local API.

Here's how the cloud version of the product is implemented:

We also offer a premise based version of the service. This operates behind your firewall and within your secure data center. Gyst CX for premise based installations can run on any internal server you control. Specifications for the server are available by reaching out to our engineering team here.

Here's how the premise-based version of the product is implemented:

Drawing on our many years of experience in the field of voice user interface design and adaptive technologies, we designed Gyst CX from the ground up to be secure, reliable and highly scalable. We also designed it to be extremely fast and very easy to use in new and existing voice applications.

And Gyst CX has fault tolerance built in; though the service is highly reliable and scalable, if for any reason Gyst CX were to become unavailable, your voice applications would simply continue to run without personalization, just as they do today.

If you would like further details on our implementation and architecture, please contact an engineer at Gyst here.

How Gyst CX works in a phone call

Gyst CX provides anonymous personalization for the caller. The beauty of this method of personalization is that it adjusts the user experience based on their exhibited behavior - not on a stored, static user profile. So there's no need to pass account numbers, PIN's or any other type of personal information to Gyst CX in order to achieve a significant level of personalization.

Gyst CX brings the caller experience to life. It measures, analyzes and ultimately personalizes the experience to suit the skill, expertise and behavior of callers in the IVR. Every caller gets their own unique experience, custom tailored on the fly to suit their individual skill and the environment from which they are calling.

Faster, or more skilled and accurate callers hear the voice interaction at gradually increasing playback speeds (words per minute spoken), throughout the call. Slower, less skilled or less knowledgable callers hear the dialogue progress at a slower pace. In addition, struggling callers get additional instructions and time to respond, while faster callers may hear abbreviated instructions in order to speed them through the dialogue.

Think of the expert user calling their bank several times a month - they are speeded through, just like drivers in the express lane. Less skilled callers may be elderly, hard of hearing or simply using a mobile phone in a noisy or or distracted environment.

In all cases, Gyst CX gives the the caller experience they want. That helps them self-serve in the IVR and get the answers they need without getting frustrated by a system that won't make allowances for them the same way a good customer service representative would.

Why this matters to the enterprise

While user-personalization has had demonstrated success for web based interactions, it has yet to be fully leveraged in the handling of self-service phone calls. Advances in speech technology such as ASR, Natural Language Understanding, Caller-Directed Dialogues and Web Profiles are excellent enabling technologies, though these are only part of the solution. Used in conjunction with a well designed Voice User Interface or VUI, they represent a significant improvement over earlier technologies. However, one important design factor that has until recently been overlooked, is the individuality and in-call behavior of the telephone callers themselves.

Every caller to your speech application has his or her own individual set of aural, speech, hand-eye coordination (as used in DTMF keypad entry) and material comprehension skills. Add to this environmental variables such as background noise, poor mobile phone signals and caller distraction and it becomes clear that each call to the IVR System is truly a unique interaction.

This is one of the main reasons human operators are so good at handling any type of call – they can handle the dynamics of human conversation intuitively and with ease. Your callers know this all too well and will opt for an agent the first time your speech system fails to be productive for them.

To the extent that the speech application can monitor and adjust to the behavior of a particular caller during the call, a proportionate number of your automated calls can be more efficient and productive. While a well designed call script with optimal structure and content, intentional pauses, grammar tuning and context forming are excellent design principles, the system falls short if it does not consider the real-time behavior of the caller just as a human would under the same circumstances.

Businesses spend over $110 billion per year on call center labor and software in the United States alone. Most of these calls are automated self-service calls, the kind that require you to press buttons or methodically speak your way towards an answer. Now, while most people find these systems frustratingly annoying, the economic reality is that they do save businesses costs when handling customer service and other inquiries.

Not surprisingly, over half of the 270 billion customer service calls in the U.S. go unresolved, often because this technology not easy to use. This results in lost business, lost opportunities and a lot of frustration for callers.

That said, for banks, credit card companies, airlines, prescription refill and technical support lines - hundreds of millions of calls per day are more costly and frustrating than they need to be.

Measurable Results

Our technology has been (and continues to be) production proven over several hundred million self-service telephone calls to date. The measured results, as tabulated in our scientific white papers during these live interactions indicate...

"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."

Another paper indicates...

"For the sample medical insurance voice application, analysis using 95% confidence intervals indicated improvements in IVR Utilization of about 17.24% - 20.44%, a reduction in First-Attempt Caller Input Errors of about 1.02% - 1.75% (relative reduction ranging from 4.7% - 8.0%) and a reduction in Average Handle Time of .49% when incorporating adaptive functionality."

The figures below indicate graphically the measured savings and performance of the technology when deployed in production environments.

Translated into Business Benefits

As a result of shorter calls, increased automation and an interface that improves the caller experience by adjusting to their skill levels, the following benefits are provided:

Skilled callers get express service: No need to get aggravated by long, laborious voice prompts - especially when they do not remember all parts of the call flow.

Novice callers get special attention: They get the information they need without getting frustrated and eventually pushed to a CSR who may ask them to repeat the steps already taken to solve their problem.

Unfamiliar callers become repeat customers: Callers that have a bad experience with your voice application will rarely return to use it again if they don’t have to. Allowing these callers to have more time to adjust to using the system encourages repeated use instead of instilling bad habits like zeroing out.

Salvaging self-service for mobile users: Poor cell signals and noisy backgrounds can exacerbate an already frustrating automated call experience. Allowing more time can save the call and the experience.

Distracted callers do not need to hang up: Gyst CX allows your IVR to make adjustments for the caller rather than forcing them to hang up only to have them call back later, or needlessly take up the time of a CSR.

Summary

With Call Centers, Enterprise IT Departments and ASR based hosting centers recognizing the economic benefits of automated calls versus using an agent, the trend is towards longer, more complex and information-rich speech applications. Enabling technologies such as the Web-Centric IVR, speech enabled dialogs, natural Language Understanding and Customer-Directed Dialogs serve to help further this trend. With this increased caller interaction, leveraging the benefits Gyst CX offers several direct and indirect benefits.