Outcomes overview

AI-generated summary

Genesys Cloud's AI-powered Predictive Engagement service uses machine learning models tailored to each business to predict customer outcomes by analyzing website visitor navigation, shopping cart activity, and interactions in a GDPR-compliant manner with anonymized data. Organizations can create up to 100 outcomes with scoring enabled on up to 10 outcomes simultaneously, with automatic model training initiating within 24 hours of outcome creation and completing before the next business day. Each outcome score represents the real-time likelihood that a visitor will achieve a defined business objective, updating continuously as visitors navigate the website and interact with content. Agents can view visitor outcome scores alongside complete journey context data, and scores can automatically trigger action maps to enhance customer engagement. The system features fully automated nightly model retraining using the last seven days of user data, allowing agents to continue normal operations during retraining while predictions rely on the previous model version. Model accuracy depends on dataset size (several hundred positive examples recommended), total journeys recorded, outcome frequency, and richness of visitor events, with prediction accuracy improving over time as more data and achieved outcomes accumulate. IP addresses can be excluded to prevent internal events from skewing model results. Genesys Predictive Engagement monitors all visitor arrival methods and webpage interactions to gather outcome probability data, with models continuously evaluated and refined on fresh data to deliver increasingly accurate predictions for business objectives.

Feature deprecation: Genesys Cloud will deprecate the Journey Outcomes feature in Genesys Predictive Engagement (GPE). For more information, see .

Genesys Predictive Engagement’s AI-powered outcome scoring service learns to predict your business outcomes using machine learning models that are unique to your business.

Outcomes are events that allow you to track the achievements of a business objective. You can view the aggregated reporting on the number of achievements and their associated value. Predictive Engagement outcome scoring ability uses these outcome events to predict your business outcomes using machine learning models that are unique to your customers. You can create up to 100 outcomes and enable outcome scoring on up to 10 outcomes per organization.

Predicting outcome scores

Each outcome score represents the likelihood that the visitor will achieve the particular business outcome, based on the actions the visitor has taken so far during the session or on other activities related to the visitor that are included in the appropriate events (for example, geolocation).

The model updates a visitor’s score both up and down as they navigate your website, showing as they get closer and further away from achieving outcomes for each outcome in real-time.

For up to 10 outcomes that you define, there is a machine learning model that evaluates a visitor’s behavior against the behavior of other visitors on your website to determine the visitor’s outcome score. Your organization’s models are unique to you.

If a visitor communicates with an agent, the agent can see the visitor’s outcome scores while viewing the visitor’s complete set of journey context data. Also, the outcome scores can trigger action maps that enhance a visitor’s engagement on your site.

Note: Because our internal service handles the training and deployment of models, it is not possible to deploy customer-specific models with Genesys Predictive Engagement. Our team investigates and integrates new algorithms into the scoring service based on customer use cases.

How Genesys Predictive Engagement gathers outcome probability data

Genesys Predictive Engagement monitors all the ways that visitors arrive on and interact with your webpages. For example, if you are an e-commerce site, Genesys Predictive Engagement tracks how visitors navigate your website and place items in their shopping cart as they proceed to the checkout page.

Note:

How a visitor achieves a certain probability score is unique to your business and website.
Outcome scores and the associated data science are scored in a GDPR-compliant manner. Predictive Engagement’s data scientists work exclusively on anonymized GDPR-compliant data.

For more information, see .

Start training your models

Each of your machine learning models require training before they can make predictions.

To start the training:

Create an outcome with outcome scoring enabled. When you add a new outcome, outcome scoring is disabled by default and no model training will occur.
If you wish to use the outcome for making predictions, then enable outcome scoring on the new outcome. You can enable outcome scoring for up to 10 outcomes.
Have visitors use your tracked website. To verify user activity, use Live Now.

After you complete these steps, the model training begins automatically within 24 hours. Automated model training and predictions are performed on the original customer journey events, which are not anonymized and generally contain PII. The training process completes and the model is ready to work before the start of the next business day.

Note: Initially, you see only a green bar with a check next to it in the Outcome Scores section. This bar indicates that the outcome condition was met. You can see the outcome scores after your model is trained.

Ongoing training

The model training process is fully automated so your models are always up to date and change as your customer behaviour or website changes. You do not need a data scientist to start, monitor, or maintain the training. Your model is retrained nightly using the last seven days of your user data. Also, your model is evaluated periodically and retrained on fresh data.

While the model is undergoing retraining, outcome scores are predicted using the previously trained version of the model. During the training process, agents can continue working as normal.

Improve predictions

In general, the longer your models run and the more data they evaluate, the better their predictions are.

The best way to improve a model’s predictions is to increase the number of achieved outcomes. In general, your dataset should contain several hundred positive examples for your model to be adequately trained to make reliable predictions.

Other factors can affect the accuracy of your model’s performance, including:

Total number of visitor journeys recorded
Frequency that an outcome occurs in the data
Richness of events that the visitor produces

Note: You can to prevent events generated internally from influencing your models.

[NEXT] Was this article helpful?

Get user feedback about articles.