Personalizing Customer Self-Service at Scale with Versay’s CUE Analytics

Personalizing Customer Self-Service at Scale with Versay’s CUE Analytics

As customers, we want personalized experiences. We want to be treated as individuals and valued each time we interact with a company. Yet, while personalized service is already driving content marketing experiences we receive (emails, web), it has been a bit of a challenge and expensive to get personalization at scale when we use self-service channels.

CUE Versay.

As a partner in Avaya’s A.I.Connect initiative, Versay brings machine learning and advanced analytics to self-service applications running on the Avaya Aura® Experience Portal. By adding CUE Analytics to the Experience Portal environment and self-service applications, Versay aggregates in-call data and predicts individual customer behavior. In turn, this allows self-service applications to adapt their interaction on a caller-by-caller basis, offering a true contextual and personalized experience. With CUE Analytics, you can better understand how customer-facing applications are performing by leveraging large data sets of interaction metrics for intelligent insights, and then offer AI-driven, context-aware, and individualized services across all channels.

CUE Analytics uses machine learning to build models that allow the self-service application to personalize and expedite the experience. With CUE Analytics you may design your application to do the following:

  • Pick Up Where You Left Off: Let callers who were dropped mid-interaction return to the same spot, without prompting a second time.
  • Customer Intent Prediction: Use past interactions to guide callers to the next logical step, such as prompting existing customers with outstanding orders at the start of the interaction to ask if they want a shipping update.
  • Caller Transfer Prediction: Determine which callers are likely to transfer to an agent, and use different self-service techniques (simpler menus, directed dialogs) to limit or avoid that need.
  • Excessive Caller Identification: Define the level of repeat caller frequency for excessive callers and determine the best way to handle these calls to address customer frustration and reduce the impact to an organization’s telephony infrastructure.

The experience a caller has through any of these use cases can vary from user to user, or even interaction by interaction for the same caller. Implementing the machine learning approach offered by CUE Analytics is a straightforward three-step process:

  1. Instrument your application to post data to CUE Analytics in real-time. Use Avaya Orchestration Designer along with the Versay CUE Instrumentation Adaptor (a pluggable data connector) to expedite this step.
  2. Monitor the application while CUE Analytics builds the models. Once the data is posting to CUE Analytics, use the dashboard to monitor the data that is aggregated in real-time. Once you have the data and insights, you may uncover areas of your self-service experience that seem to be underperforming or could benefit from further investigation. With immediate data, CUE Analytics users can quickly spot answers to questions such as: Is there a path that seems incomplete? How can we reduce the call duration? Are callers transferring from unexpected points in the call flow? While you are viewing the data, Versay’s AI-based data analysis is building machine learning models to gain insights into the customer behavior. After a brief period of time, the models will be ready to be used by the application.
  3. Modify your application. While CUE Analytics is learning from the data and building models, you may work with Versay or Avaya Professional Services team to modify the application to be able to query the data and insights from CUE Analytics during the live call.

Learn more about CUE Analytics and reach out to Versay for a demo of CUE Analytics through the DevConnect Marketplace.

Views All Time
Views All Time
664
Views Today
Views Today
5