During production trials from March 8, 2012 through March 16, 2012 adaptive technology improved the success rate of automated calls at a client site by 1 percent.

The client, an unnamed IVR hosting center that supports thousands of ports and dozens of voice applications, segregated out select groups of adaptive and non-adaptive ports for exact performance measurements. The adaptive ports were using Interactive Digital’s Adaptive Audio (www.interactive-digital.com) software.

As Figure 1 below shows, the call center received a total of 37601 calls on the non-adaptive ports during this period while 37811 were received on the adaptive ones. Of those calls, respectively 10110 and 10545 were considered by the client to be successful. To meet the criteria for success, a caller had to receive information (bank balance, airline flight information, medical claim details etc.) and then either hang up or continue their call with an agent.

The technology, if used properly, provides motivation for significant upgrading of existing self-service installations.

According to ASR News, the speech market will continue to grow at a healthy clip, as illustrated in Figure 1 below.

Figure 1 Telephone Self-Service Usage Projections
(Billions of Minutes)

In 2010, the total self-service installed base was 8.6M ports worldwide. Figure 2 shows the geographic breakdown for these port deployments.

Figure 2

Total Self-service Ports Installed by Geographic Region

The projected CAGR for this market for 2010 – 2015 is 7.3% with the outsourced sector leading the charge. Virtually every enterprise has installed some form of telephone self-service. Additionally, in 2010 there were:

• A total of 889,640 self-service port shipments, of which 79.54% were for the Customer Premise Equipment market.

• A total of 75.9B DTMF self-service inbound call minutes worldwide with Financial Services being the segment leader at 18.76B minutes.

• A total of 14.98B Speech self-service inbound call minutes in worldwide with Financial Services again being the segment leader with 4.16B call minutes.

Get the full White Paper here

Figure 1 shows how an “engagement threshold” exists for the caller when they use an IVR application the first few times. Notice that, though it may be slightly different for Speech and DTMF, there is a significant threshold after 2 – 3 successful interactions by the caller. This critical period is when callers ask themselves whether this automated process will work for them so they don’t have to wait for a CSR, or whether they are wasting their time when they may end up talking to a CSR anyway.

Figure 1 - The Caller Engagement Threshold

Reaching this “buy in” point is critical to the success of any voice application. The likelihood that a returning caller will use the automated system depends heavily on their past experience with that same voice application. If their prior experience(s) were positive, they will view the IVR as a great shortcut to make their life easier. If not, they will view it as a complete waste of time and avoid it altogether. This kind of loyalty or distain is very similar to how we treat store personnel whom we know from prior experience to be either not helpful, rude or ineffective. We just go around them.

Some of our earlier white papers discuss the human, environmental and cultural factors eroding the effectiveness of IVR applications. This paper discusses the impact callers using mobile phones have in the equation.

Get this white paper now here.

Based on production metrics gathered at various installations,the figure below illustrates the relationships between average call length, the number of script levels and the effectiveness of adaptive technology at optimizing the call process.

These data indicate improvements in the Average Handle Time (AHT), Average Handle Rate (AHR), IVR Utilization (IVR turns per call) and Caller Input Error Rates.

The benefits of adaptive technology to optimize self-service telephone calls vary based on the design, content and average call duration of the speech application. Applications must provide a sufficient amount of caller interaction to make the technology worthwhile. In general, the more levels of scripting and the higher the average automated call duration, the greater the benefit. Applications with caller authentication work particularly well with adaptive technology.

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.

This paper details the results of several production trials Interactive Digital conducted with clients to determine the effectiveness of using adaptive technology to optimize the efficiency of self-service telephone calls. The paper also examines how the technology was used to enhance and personalize the automated experience for individual callers.

For further details, see the white paper here

This audience uses a wide variety of personal, mobile and landline based devices in various modes to access information over the phone.

Some facts and figures:

• At the end of 2011, there were 6 billion mobile subscriptions, according to the International Telecommunication Union.

• Mobile subscriptions outnumber fixed lines 5:1 (more so in developing nations)

• According to the US Census Bureau, the hearing loss population in the US has grown to over 31.5 million

• Linguists estimate that half of the world’s population is bilingual and there are about 5,000-6,000 different languages spoken in the world today.

• People of a particular culture or regional dialect may be comfortable with long pauses at the conclusion of a sentence, while people of another may find this demonstrates disinterest, lack of attentiveness and even disrespect.

Mobile phone use globally in 2011

Language, Dialect, Age, Culture, Gender and Communications Technologies impact the effectiveness of voice communication between humans and computers. Add to this the fact that the world economy is constantly moving towards true globalization and a mixing of cultures, belief systems, languages and customs and it is easy to see why the norms of application design that once applied to a more static and homogeneous population no longer apply today.

These factors are discussed in detail in a new white paper titled “Caller Demographics and Mobile Technology Considerations in the IVR ” and available on our Customer Think site here

Individual callers speed and accuracy determined whether (and by how much) the audio playback rate was increased or decreased at each IVR script Interaction Point (IP).

An IP might be as simple as answering yes/no, selecting from a menu, entering a 16 digit credit card number or anything in between.

A caller that behaved as an expert throughout the call would experience an audio playback speed adjustment profile that went from 100% to 108% and then to a final maximum rate of 112% of normal playback.

A caller that was not quite an expert, but better than average, experienced an adjustment profile of 100%, 105%, 108% and 110%.

Callers with less than average speed and accuracy experienced similar adjustment profiles in the opposite direction – 100%, 95%, 92% and so forth.

For callers of all skill levels, the audio rate was corrected when callers went from behaving like an expert to behaving like a novice (and vice-versa) during the call.

Finally, callers that navigated the call script with average skills heard what they hear today – 100% all the way.

The Adaptive Audio software performed the WPM adjustments according to its internal, proprietary algorithms after it had gathered a sufficient calibration sample for caller skill levels at each script IP during production.

While the production run referenced in the earlier blog entry showed results indicating that over 80 percent of all callers qualified themselves (according to the above described WPM adjustment process) to speeds other than the “Normal” speaking rate, the results here showed a different type of result.

As Figure 1 below indicates, there were a total 1913 IP’s or 1.66 IP’s per call for the adaptive calls versus 1807 IP’s or 1.52 IP’s per call for standard. This represents a 9.2 percent improvement for adaptive over standard in terms of IP’s per call (IVR Utilization).

Figure 1 also shows that there were 278 caller input errors on 605 adaptive calls resulting in .17 errors per call. On the standard calls, this rate was .19 errors per call, resulting in an overall error rate reduction of 10.5 percent, again in favor of the adaptive calls.

Figure 1
IVR Utilization and Error Rate Improvements

It should be noted here that the low number of IP’s per call was due in large part to the fact that this production trial was carried out at a service provider that supports many different types of voice applications. Some of those apps simply announce a message and transfer the caller – no opportunity for adaptation here. Other apps just direct callers via one or two audio messages. The numbers collected and shown here reflect these conditions.

The benefits described above came largely from the calls with three or more IP’s.

It is also worth noting that these benefits were produced with basic adaptive functionality – only the audio playback speeds were adjusted to match caller skills and other adaptive features like Adaptive Timeout Extensions and Dynamic Application Smoothing were not implemented during this particular trial.

To learn more about how dynamically adjusting the call experience to suit individual callers can help your bottom line, contact Interactive Digital today.