(Created target blank page For Version: PSAAS:Public) |
(Update with the copy of version: draft) |
||
| Line 1: | Line 1: | ||
| − | <!-- | + | = Genesys Predictive Routing = |
| + | __NOTOC__ | ||
| + | ==''What is Genesys Predictive Routing? ''== | ||
| + | |||
| + | Genesys Predictive Routing (GPR) draws on accumulated agent, customer, and interaction data, enabling you to analyze omnichannel interactions and outcomes and generate models to predict outcomes. From this analysis, combined with machine learning, you can determine the best possible match between waiting interactions and available agents, and then route the interactions accordingly. | ||
| + | |||
| + | In addition, you can report on the predicted versus actual outcomes. The actual outcome is also used to further train the machine-learning model, improving the accuracy of predicted outcomes between similar customer profiles and agent profiles. | ||
| + | |||
| + | You can: | ||
| + | *Review [[Documentation:GPM:help:cfgAgents#discflds|agent]], [[Documentation:GPM:help:cfgCustomers#discflds|customer]], and [[Documentation:GPM:help:Datasets#datasetList|interaction]] data that is automatically collected from Genesys Info Mart and the Designer Analytics SDR. | ||
| + | *Use the [[Documentation:GPM:help:LEReport|Lift Estimation report]] to generate an estimate of the potential improvement in your KPIs using GPR. Use this report to direct your implementation toward the metrics that show the most promise for immediate results. As you work with GPR, the insights into your data and how your environment functions can open new avenues for improvement in additional areas. | ||
| + | *Use the [[Documentation:GPM:help:FAReport|Feature Analysis report]] to identify which factors most strongly affect various KPIs. The results enable you to create more effective predictors and models. | ||
| + | *Use the [[Documentation:GPM:help:AgtVarReport|Agent Variance report]] to determine where differences between agent effectiveness in different scenarios offers potential for improved outcomes. | ||
| + | *Create [[Documentation:GPM:help:Predictors|predictors]] and [[Documentation:GPM:help:Models|models]] based on your imported data. | ||
| + | **[[Documentation:GPM:help:Models#modelReports|Model Quality]] report: Provides an analysis of how well the model is performing. | ||
| + | **[[Documentation:GPM:help:Models#modelReports|Agent Coverage]] report: Indicates how many agent models were built, as a function of the total agents available. | ||
| + | *Review and test the performance of your [[Documentation:GPM:help:Analysis|predictors and models]]. | ||
| + | *Monitor [[Documentation:GPM:help:Jobs|jobs]] that you are running or have run. | ||
| + | *Create [[Documentation:GPM:help:Dashboard|dashboards]] that enable you to quickly view items you use most often. | ||
| + | |||
| + | Access the complete [[Documentation:GPM:help:Welcome|Help]]. | ||
| + | {{NoteFormat|Some features that are described in the Help are applicable only to on-premise deployments.}} | ||
| + | |||
| + | <!--{{CloudStep_Stack | ||
| + | |title= | ||
| + | |text= | ||
| + | Watch the video for a quick overview of GPR functionality. | ||
| + | |||
| + | '''Note:''' Some features that are described in the video are applicable only to on-premise deployments. | ||
| + | |video=xxxxxxxxx | ||
| + | }}--> | ||
| + | |||
| + | [[Category:V:PSAAS:Public]] | ||
Revision as of 20:30, December 29, 2018
Genesys Predictive Routing
What is Genesys Predictive Routing?
Genesys Predictive Routing (GPR) draws on accumulated agent, customer, and interaction data, enabling you to analyze omnichannel interactions and outcomes and generate models to predict outcomes. From this analysis, combined with machine learning, you can determine the best possible match between waiting interactions and available agents, and then route the interactions accordingly.
In addition, you can report on the predicted versus actual outcomes. The actual outcome is also used to further train the machine-learning model, improving the accuracy of predicted outcomes between similar customer profiles and agent profiles.
You can:
- Review agent, customer, and interaction data that is automatically collected from Genesys Info Mart and the Designer Analytics SDR.
- Use the Lift Estimation report to generate an estimate of the potential improvement in your KPIs using GPR. Use this report to direct your implementation toward the metrics that show the most promise for immediate results. As you work with GPR, the insights into your data and how your environment functions can open new avenues for improvement in additional areas.
- Use the Feature Analysis report to identify which factors most strongly affect various KPIs. The results enable you to create more effective predictors and models.
- Use the Agent Variance report to determine where differences between agent effectiveness in different scenarios offers potential for improved outcomes.
- Create predictors and models based on your imported data.
- Model Quality report: Provides an analysis of how well the model is performing.
- Agent Coverage report: Indicates how many agent models were built, as a function of the total agents available.
- Review and test the performance of your predictors and models.
- Monitor jobs that you are running or have run.
- Create dashboards that enable you to quickly view items you use most often.
Access the complete Help.
Important
Some features that are described in the Help are applicable only to on-premise deployments.
Comments or questions about this documentation? Contact us for support!