Optional sources of data for predictive routing

AI-generated summary

Genesys Cloud's predictive routing system leverages multiple optional data sources—including web surveys, sentiment analysis, external contacts, agent profiles, and participant data—to enhance routing accuracy and prediction capabilities. Agent profiles should contain employment information, certifications, ACD skills, and language proficiencies for agents assigned to predictive routing-enabled queues. Participant data attributes must adhere to specific formatting requirements: alphanumeric names with underscores only, values limited to numeric or boolean formats, high coverage across interactions, and low cardinality strings. The system optimizes routing decisions using participant attributes such as customer VIP status, contract type, intent, propensity to churn, and WEM external metrics. The Workforce Engagement Management (WEM) API integration transmits daily agent performance data to build comprehensive agent profiles, enabling interactions to route to agents with appropriate specialization and performance levels. Organizations can configure metrics and permission settings to tailor routing optimization to their specific needs. To prevent algorithmic bias, personally identifiable information (PII) should be avoided in participant data attributes. Genesys Cloud requires all attributes to contain explicit true or false values with no defaults and treats string values as case-sensitive while ignoring long strings. For optimal functionality, attributes should be attached to all or most conversations; sparse attribute attachment limits routing utilization. String-type attributes must maintain low cardinality, as high cardinality values are excluded from routing decisions, though this restriction does not apply to numeric attributes. Recommended participant data attributes include CUSTOMER_IS_VIP (true/false), CONTRACT_TYPE (silver/gold/platinum), INTENT (numeric values 1-6), and PROPENSITY_TO_CHURN (numeric values, typically 0-100). Daily metric submission through the WEM external metrics API is recommended for optimal model training and improved overall performance outcomes.

While some of the required data is available for Genesys predictive routing to consume readily, you can make other additional data available for predictive routing to use.

If available, predictive routing uses data from the following sources:

If your organization has web survey enabled and you have enough survey data available for agents assigned to GPR-enabled queues, predictive routing uses the survey data for model training and routing prediction purposes.
If your organization has sentiment analysis enabled, predictive routing uses the data for routing prediction.
If your organization has imported external contacts to Genesys Cloud, predictive routing uses the data for routing prediction. For more information, see About External Contacts.
Agent profile data
Participant data
WEM external metrics

While not mandatory, the availability of the following optional data can help your organization achieve better routing results.

Note: Before you save the information, ensure that the text is spelled correctly.

Agent profile dataClick to expand

For the agent profile data to be considered for routing decisions, make sure you have the following information available for a maximum number of agents who are working on queues that have Genesys predictive routing enabled.

Add agent’s employment and certification data. See Standard profile fields.
1. Click People & Permissions > People.
2. In the Search field, to filter the type the first few letters of the person’s first or lastname.
3. Click the Person Details tab and click View Edit Mode.
4. Click Add new section and enter the following data:
  Section Field
  On the Person Details page (below the profile picture) Department
  HR
  Hire Date
  Employee Type
  Skills & Certifications Certifications
Add the agent’s ACD skill and language data. See Add an ACD skill or language to a user.

Section	Field
On the Person Details page (below the profile picture)	Department
HR	Hire Date Employee Type
Skills & Certifications	Certifications

Participant dataClick to expand

For customer data to be considered for routing decisions, customers must have attributes, or participant data, assigned to them. The participant data must meet the following conditions:

Participant data	Conditions
Name of attribute	Can contain: Alphanumeric characters Underscore For predictive routing purposes, participant data attributes are considered case-insensitive. Genesys highly recommends not to have two participant data attributes with the same name. Note: If you use special characters such as spaces, dots, and commas, predictive routing does not consider the attribute for routing decisions.
Value of attribute	Value can contain: Numeric values (integer or decimal) Boolean (true/false). Ensure that every attribute contains either a true or false value; Genesys Cloud does not use any default value if the value is not populated. String values String values are case-sensitive. Long strings are ignored.
Availability	Genesys recommends that you attach attributes to all or most of the conversations. If an attribute is attached only to a small volume of interactions, predictive routing does not use the data for routing decisions.
Cardinality	If attribute values are of string type, ensure that the cardinality of those values is low. If cardinality is high (for example every conversation has a different value for a certain attribute), predictive routing does not use the data for routing decisions. This cardinality condition does not apply to attributes with numeric values.
PII data	Genesys recommends that you do not add any PII as participant data attributes as either keys or values.

Note: Any participant data, which satisfies these criteria may be used by predictive routing models. Therefore, Genesys recommends that you review whether any attributes might introduce bias such as race or gender and exclude them.

The following are examples of participant data attributes that enhance the accuracy of predictive routing decisions:

Attribute name	Description	Allowed values
CUSTOMER_IS_VIP	Is the customer a VIP	true/false
CONTRACT_TYPE	Type of contract the customer has	silver/gold/platinum
INTENT	Intent of customer	1,2,3,4,5,6
PROPENSITY_TO_CHURN	Propensity of customer to churn	Any number (may be between 0-100)

Workforce engagement management external metricsClick to expand

Use the workforce engagement management (WEM) external metrics API to send information about the performance of agents. This helps build the agent profile and enables Genesys Cloud to route the interactions to the best agent depending on their area of specialization and performance.

To optimize the routing decision, define the metrics that best capture your agents’ performance. Genesys recommends that you send the information daily for model training purposes. For more information about the WEM API, see Measuring Employee Performance using metrics external to Genesys Cloud. For more information about metrics configuration and permissions, see Configure external metrics for performance scorecards.

[NEXT] Was this article helpful?

Get user feedback about articles.

Section	Field
On the Person Details page (below the profile picture)	Department
HR	Hire Date Employee Type
Skills & Certifications	Certifications

Section

Field

On the Person Details page (below the profile picture)

Department

Hire Date
Employee Type

Skills & Certifications

Certifications

Participant data

Conditions

Name of attribute

Can contain:

Alphanumeric characters
Underscore

For predictive routing purposes, participant data attributes are considered case-insensitive. Genesys highly recommends not to have two participant data attributes with the same name.

Note: If you use special characters such as spaces, dots, and commas, predictive routing does not consider the attribute for routing decisions.

Value of attribute

Value can contain:

Numeric values (integer or decimal)
Boolean (true/false). Ensure that every attribute contains either a true or false value; Genesys Cloud does not use any default value if the value is not populated.
String values
- String values are case-sensitive.
- Long strings are ignored.

Availability

Genesys recommends that you attach attributes to all or most of the conversations. If an attribute is attached only to a small volume of interactions, predictive routing does not use the data for routing decisions.

Cardinality

If attribute values are of string type, ensure that the cardinality of those values is low. If cardinality is high (for example every conversation has a different value for a certain attribute), predictive routing does not use the data for routing decisions. This cardinality condition does not apply to attributes with numeric values.

PII data

Genesys recommends that you do not add any PII as participant data attributes as either keys or values.

Attribute name

Description

Allowed values

CUSTOMER_IS_VIP

Is the customer a VIP

true/false

CONTRACT_TYPE

Type of contract the customer has

silver/gold/platinum

INTENT

Intent of customer

1,2,3,4,5,6

PROPENSITY_TO_CHURN

Propensity of customer to churn

Any number (may be between 0-100)

Optional sources of data for predictive routing

[NEXT] Was this article helpful?

Loading...

Optional sources of data for predictive routing

[NEXT] Was this article helpful?