Action classification

By default, promotional actions such as promotional emails are presented to customers if they fit the arbitration criteria, contact policies, and outbound limits that you specified. You can designate an action as transactional, so that it is delivered to the customer according to the contact policies and arbitration criteria, but without applying outbound limits.

Starting in version 8.7, you can additionally designate an action as mandatory. A mandatory action could be communication related to compliance (for example, a notification about an increase in interest rates), network outages, or weather events. Mandatory actions are always delivered to customers, regardless of contact policies, outbound limits, or arbitration criteria.

For more information, see Next-Best-Action configuration.

Enhancements to action bundles

Your Next-Best-Action strategy can now recommend Advertised bundles to customers. Advertised bundles are preconfigured groups of products that are offered together for a specific price, as opposed to Personalized bundles, which are created by the Next-Best-Action strategy based on the latest next best actions selected for the customer. Starting in Pega Customer Decision Hub 8.7, the Pega Next-Best-Action Advisor component allows the strategy to offer an Advertised bundle to a customer, if it is determined to be the next best action.

Additionally, you can now use the advanced bundling capabilities typically required of Pega Next-Best-Action Advisor without implementing Pega Next-Best-Action Advisor itself. To implement this capability in your organization, download and install the new Advanced Bundling Component, available on Pega Marketplace.

For more information, see Applying communications accelerators.

Learning from orders placed

Pega Customer Decision Hub provides a new service that you can configure to enable the application to learn from orders placed. The service allows adaptive models to learn from the most relevant outcome in the Agent Assisted channel, where the Accepted outcome might be less relevant than the Ordered outcome.

For more information, see Configuring adaptive models for the Agent Assisted channel.

Success reporting for Agent-Assisted

Reporting is usually an afterthought when planning projects, but you should build your solution with reporting in mind. In Pega Customer Decision Hub version 8.7, Follow the best practices for recording data to ensure successful reporting in agent-assisted channels. Along with other data, store the following in the Interaction History:

• Agent Impression
• Impression
• Accepted
• Ordered

For more information, see Best practices for recording data to facilitate reporting in Agent-Assisted.

Finer arbitration adjustments

Next-Best-Action Designer now provides you with better control of how actions and treatments get prioritized, thanks to the ability to make finer adjustments to next-best-action arbitration, so that only relevant messages get communicated to customers and you can determine the source of propensities.

For more information, see Prioritizing actions based on customer relevance and business priority.

Contact policies enhancements

Next-Best-Action Designer constraints now allow you even more flexibility and control over how often you communicate with your customers by using outbound channels. You can now add more than one customer contact policy to each channel, which means you can add multiple time periods for each channel. Additionally, in Pega Customer Decision Hub version 8.7, adding new time tracking periods is easier.

For more information, see Controlling the number of customer contacts with outbound limits.

Higher predictive power with adaptive gradient boosting

Pega Platform version 8.7 introduces a new adaptive gradient boosting algorithm in Pega Adaptive Decision Manager with a higher predictive power that predicts propensities for all the available actions. It provides highly personalized and relevant actions to individual customers, achieving true one-to-one customer engagement.

For more information, see Adaptive gradient boosting overview and Adaptive Gradient Boosting - a Pega Whitepaper.