Genesys Predictive Routing for Sales (SL06) for Genesys Engage on premises

From Genesys Documentation
Jump to: navigation, search
This topic is part of the manual Genesys Engage On-premises Use Cases for version Current of Genesys Use Cases.
Place revenue generation at the center of your routing decisions by using AI to match each customer opportunity with the best agent

What's the challenge?

Your existing routing strategy doesn’t use machine learning to adapt to the changing patterns of interactions and optimize for sales conversions. You want customers to speak with a rep who can fulfill their need quickly and is predicted best to increase revenue, based on customer journey. Don't let your CX scores suffer!

What's the solution?

Create a differentiated experience by connecting customers with your best-fit sales reps. Genesys Predictive Routing provides the finest grain matching between sales reps and customers and appropriately routes the interaction on the customer’s preferred channel.

Use Case Overview

Story and Business Context

Business leaders want to improve their business Key Performance Indicators (KPI), leverage the innovation in Artificial Intelligence and drive business decisions with the abundance of data and context available in their business. Predictive Routing uses machine learning to support optimization of Sales KPIs.

A Sales KPI is a metric measuring the sales outcome of an interaction, in contrast to Service KPIs, which measure a Customer Experience or efficiency outcome. Sales KPIs can be a sales conversion rate, a sales revenue amount, a retention rate, a collection promise to pay. This use case focuses on improving revenue for inbound voice calls, but can also be extended to other sales-related KPIs. The impacts of choosing another KPI or another channel type are documented in this use case wherever applicable.

Predictive Routing also applies to optimize Services KPIs. See Genesys Predictive Routing for Customer Service (BO06) for Genesys Engage on-premises.

Traditional routing is designed to match customers to agents through skills-based or group-based logic rather than improving KPI. Unlike traditional routing, Predictive Routing uses machine learning to find signals in historical data to build a predictive model. This model improves KPIs by ranking agents before making the match with customers. This model also addresses the operational challenges that occur in understaffing and overstaffing scenarios while balancing the service level with improving KPI.

Predictive Routing has built-in A/B Testing to demonstrate the uplift of the KPI provided through use of machine learning. Predictive Routing leverages a variety of Genesys or third party data sources in order to build high quality predictors.

Use Case Benefits*

Use Case Benefits Explanation
Improved Employee Satisfaction Increased sales success leads directly to improved satisfaction for sales reps.
Improved Net Promoter Score Routing prospects to the sales reps best able to handle their sales request improves the customer experience.
Increased Revenue Machine learning-based matching of sales reps to prospects based on sales value directly increases revenue.
*You can sort all use cases according to their stated benefits here: Sort by benefits


Consider a retail bank that wants to upsell credit cards to its existing customers. Depending on the customer attributes (such as income), the bank wants to maximize both the conversion rate and the credit limit that the customer accepts, resulting in a higher overall revenue. This use case is based on a measure of sales revenue driven from a Sales reporting application (such as CRM).

The underlying premise of this use case is that a customer interaction is associated to a credit card offer, either from the explicit customer intention from IVR, web, or mobile or from a business rule such as next best action. Next best action is out of scope of this use case.

The Contact Center Manager or Business owner wants to increase overall revenue generated per agent. The Predictive Routing solution can help with achieving this objective.

Predictive Routing:

  • Uses machine learning, a subset of Artificial Intelligence, to compare feedback of the actual outcome with the predicted outcome, helping to improve future agent-to-customer matches.
  • Ranks agents predicted to maximize the expected revenue per interaction.
  • Provides the finest grain match of customer contact with agent to help maximize revenue per agent. Provides an uplift on revenue using continuous learning to rank the expected revenue for agents servicing customers.

The direct result is that the average revenue per interaction increases. Predictive Routing usually also influences adjacent service KPIs like first contact sale, CSAT or NPS, handle time, and transfers. It is a common best practice to monitor all Sales KPIs and adjacent Service Levels to evaluate all impacts (out of scope of this use case).

Use Case Definition

Business Flow

Predictive Routing for Sales

This business flow shows the use case from the perspective of the customer and agent.

Business Flow Description

  1. The customer contacts the company using a voice call, as part of the inbound voice use case.
  2. The context data is captured depending on the interaction and engagement type.
  3. Genesys queues the interaction.
  4. Predictive Routing ranks the agents according to the expected revenue for that specific interaction and returns a ranked list with values.
  5. Genesys checks if the value for at least one agent is above the configured threshold.
  6. If no agents are available within the configured timeout, the routing expands the potential target pool of agents, by reducing the required threshold.
  7. If agents above the threshold are found, Genesys distributes to the best available agent based on the predictive model (the agent with the highest rank) and the routing rules.
  8. The agent disconnects the interaction.
  9. Optional: The outcome data is mapped to an InfoMart attribute (for example, a disposition code or custom key value pair)
  10. Optional: The customer is offered a survey. The answer to the survey is stored in a third-party system.
  11. Optional: Outcome data, such as CRM sales transaction completion and value, is produced and stored by a third-party application.

Business and Distribution Logic

Business Logic

Parameters and Business Rules – Predictive Routing Revenue

Routing Step 1 The system creates an inbound interaction when a customer voice call begins. This use case supports inbound voice involving Genesys routing. See Use Case Interdependencies for details.

  • Precondition: This use case requires one or more use cases handling inbound interactions.

Routing Step 2

  • The inbound interaction use case identifies the primary intention of the customer (Service Type) and the initial target skill expression is set.
  • Any required additional customer or agent profile data available to the interaction in run time can be integrated through a project-based implementation.

Routing Step 3

  • This step queues the interaction and is designed to cover both agent surplus and customer surplus scenarios. When either one or multiple agents are available (agent surplus scenario), the flow immediately proceeds. Otherwise, Genesys queues the interaction until an agent is available (customer surplus scenario). The system starts to balance the service level with the business KPI through maintaining priority.

Routing Step 4

  • Once one or more agents are available, the necessary Customer Profile, Interaction Profile, Agent Profile, and predictor information is passed to Predictive Routing as a scoring request. The request is processed by the relevant machine learning model, resulting in a score for each available agent for that interaction. This process caters to both customer surplus and agent surplus scenarios.

Routing Step 5

  • The rank for each of the interactions against each of the agents is returned to routing to weight the customer-to-agent matching towards the agent(s) that can deliver the highest revenue.
  • In an agent surplus scenario, the score of the highest ranked agent will be compared to the configured minimum score threshold.  If the agent score exceeds that threshold, the system routes the interaction.  If not, then the interaction is held, pending either a higher ranked agent becoming available, or the threshold reducing.
  • In a customer surplus scenario, where multiple interactions are waiting when an agent becomes available, the agent’s scores for each waiting interaction are compared to the minimum score threshold.  If the agent score exceeds the threshold for at least one interaction, the system routes the highest scoring interaction for that agent.  If not, then the agent remains unassigned, pending either a lower scored interaction becoming available, or the threshold reducing.

Routing Step 6

  • The minimum score threshold is reduced over time according to the pre-configured fallback strategy.
  • The checks in Routing Step 5 are repeated regularly until an agent or interaction is identified.
  • Normal target expansion, such as relaxing skill level as configured within the underlying distribution strategy, occurs.
  • The continual re-prioritization of the interaction also occurs as do any treatments and the queued customer experience.

Routing Step 7

  • If at least one of the revenue values is above the threshold, the interaction is routed to the agent with the highest revenue.
  • The system delivers the interaction normally, handling any ring on no answer and exception situations (applicable to voice, chat or email) as defined in the underlying use case.
  • The customer and the agent are connected.

Routing Step 9

  • The outcome of the interaction is captured through the agent desktop or a server-side process. Genesys APIs are invoked automatically or after an agent action to map the outcome to a Genesys interaction attribute: custom attached data or disposition code.
  • Info Mart captures this attribute with the Info Mart interaction record.

Routing Step 10

  • Optionally, the customer receives a survey (the survey results are not connected with Genesys and are intended to evolve with the survey use cases)
  • The survey is completed (optionally) and the outcome is collected and stored by a 3rd-party application.

Routing Step 11

  • Optionally, the outcome data is produced and stored by third-party application.

Distribution Logic

The details of the distribution of an interaction to an agent are defined in the underlying inbound use cases. Refer to the preceding flow to understand how Predictive Routing influences the distribution logic.

Predictive Routing provides a routing lever that can be used to control how customer-to-agent matching behaves in customer surplus mode to distribute the interactions based on agent occupancy.

User Interface & Reporting

Customer Interface Requirements

There is no content applicable to this section.

Agent Desktop Requirements

This use case does not include specific agent desktop requirements. During the routing phase, attachment of specific data occurs that the agent visualizes.


Real-time Reporting

Predictive Routing real-time reports include:

Queue KPIs By Predictive Model

Monitor your Queue performance with the prediction scores provided by Genesys Predictive Routing to optimize your business KPI.

PRM Queue Group by Model View 3.png

Agent Group KPIs by Predictive Model

Monitor the Agent Group Performance with the volume of answered interactions by range of predicted scores provided by Genesys Predictive Routing to optimize your business KPI.

PRM Agent Group By Model View 1 3.png

Historical Reporting

The historical reports available within the Predictive Routing Data Store include:

  • Predictive Routing Operational Report tracks Predictive Routing operational statistics.
  • Predictive Routing A/B Testing Report tracks A/B testing results for Predictive Routing models and predictors.*
  • Predictive Routing Agent Occupancy Report tracks Agent Occupancy while Predictive Routing is being used to optimize routing.
  • Predictive Routing Daily Queue Statistics Report tracks KPIs for each Queue while Predictive Routing is being used to optimize routing.
  • Predictive Routing Detail Report provides interaction level detail data about Predictive Routing use and its impact on KPIs.

*A/B reports can be developed from any standard or custom Info Mart data. If the outcomes data is NOT integrated with Info Mart, the creation of A/B reports must be evaluated as a separate effort.


General Assumptions

The following use cases are exceptions where Predictive Routing cannot be integrated:

Customer Assumptions

  • Customer has all compatible versions of URS, IRD, Composer, GIM, GCXI, GII, and Pulse or upgrades have been scoped in to the project plan.
  • Customer has necessary systems and processes in place to track results and measure impact over the life of the model
  • Customer identification must be available and stored in Infomart.
  • Significant percentages of interactions require to have a customer ID linked. If less than 10 percent interactions have a customer ID, then building models may not be feasible


All required, alternate, and optional use cases are listed here, as well as any exceptions.

All of the following required: At least one of the following required: Optional Exceptions



          Workforce Engagement


                Workforce Engagement

                  On-premises Assumptions

                  • This use case is for revenue optimization but can be extended to other Sales KPIs.
                  • Customer should have one or more Genesys channels.
                  • Prerequisites: An implemented use case for one or more channels and Info Mart reporting. These use cases populate the predictors in the routing and the data necessary to build the models. This solution cannot use data that is not present.
                  • The standard deployment materials address Inbound voice interactions only, and Informart data only.
                  • The capture and analysis of Sales KPIs is not part of Info Mart out-of-box statistics and is developed during model creation.
                  • Omnichannel and outbound integrations require Genesys Product Management approval and Genesys Professional Services support.
                  • Integration of other data sources, Genesys, or 3rd-party, requires a dedicated assessment and implementation by Genesys Professional Services.
                  • Digital, Workload Management, and Outbound integrations require Genesys PS, Product, and R&D support.
                  • Routing to agents is based on skill expressions or group-based routing.
                  • Predictive Routing solution is offered to on-premises customers from the Genesys Cloud in a Cloud-only supporting Hybrid Architecture.
                  • Requires Product Management approval.
                  • The revenue definition chosen in this use case is illustrative and needs to be adapted for each project.

                  Cloud Assumptions

                  Related Documentation

                  Document Version

                  • V 1.1.3