This customer operates the busiest commuter railroad in North America, carrying approximately 200,000 customers each weekday on 947 daily trains. The company is committed to maintaining a transit system that is safe, reliable, and accessible for all and are investing in system wide improvements that will keep its transit system running smoothly for decades to come. The company is continuously working on ways to improve operations in ways that support its core values of equity, accessibility, sustainability, and cost-consciousness.
The company's contact center handles over 5,000 call per day. Many of the calls are handled via their existing Interactive Voice Response (IVR) system. The voice application running on that IVR handles inquiries for detailed point to point schedule and fare information, and for general information for commuters and occasional travelers. While the IVR solution front-ends all incoming phone calls, many callers were opting for an agent, and the handle time for automated calls was too high at 176 seconds on average.
In cooperation with the customer, we implemented our technology to conduct A/B trials on over 80,000 phone calls to determine what effect dynamically adjusting the audio playback rate of voice prompts in their IVR would have on their voice self-service performance. Existing voice prompts were speed adjusted in direct relation to individual caller skills. Novice, less skilled callers got to hear the voice prompts gradually tuned down slower to suit their ability to keep up with the dialog. Expert and more skilled callers were able to achieve their goal in the IVR more quickly. as a result, fewer callers went to expensive agents.
During the trial, audio playback speed adjustment levels of 100, 110, 114, 117, and 119 percent were used. A playback level of 100 indicates the normal playback rate of the audio, 110 represents 110 percent of normal, and so forth.
In summary, the results indicated:
Callers using speed adjusted audio had 21.2% more engagement (Conversation Turns) with the IVR over callers using standard audio. They also encountered 15.4% fewer error messages and thus, had to reenter information 15.4% fewer times.
With our technology, this client also increased the self-service rate in their IVR by around 2 percent and reduced the average handle time for voice self-service by a full 26 seconds. Regular commuters (who were familiar with the dialog flow) were able to navigate to the information they needed more quickly resulting in a better, shorter customer experience. This client realized an ROI of less than six months