- Platform Tutorials
- Introduction to Platform
- A customer experience powered by Experience Platform
- Behind the scenes: A customer experience powered by Experience Platform
- Experience Platform overview
- Key capabilities
- Platform-based applications
- Integrations with Experience Cloud applications
- Key use cases
- Basic architecture
- User interface
- Roles and project phases
- Introduction to Real-Time CDP
- Getting started: Data Architects and Data Engineers
- Authenticate to Experience Platform APIs
- Import sample data to Experience Platform
- Administration
- AI Assistant
- Audiences and Segmentation
- Introduction to Audience Portal and Composition
- Upload audiences
- Overview of Federated Audience Composition
- Connect and configure Federated Audience Composition
- Create a Federated Audience Composition
- Audience rule builder overview
- Create audiences
- Use time constraints
- Create content-based audiences
- Create conversion audiences
- Create audiences from existing audiences
- Create sequential audiences
- Create dynamic audiences
- Create multi-entity audiences
- Create and activate account audiences (B2B)
- Demo of streaming segmentation
- Evaluate an audience rule
- Create a dataset to export data
- Segment Match connection setup
- Segment Match data governance
- Segment Match configuration flow
- Segment Match pre-share insights
- Segment Match receiving data
- Audit logs
- Data Collection
- Dashboards
- Data Governance
- Data Hygiene
- Data Ingestion
- Overview
- Batch ingestion overview
- Create and populate a dataset
- Delete datasets and batches
- Map a CSV file to XDM
- Sources overview
- Ingest data from Adobe Analytics
- Ingest data from Audience Manager
- Ingest data from cloud storage
- Ingest data from CRM
- Ingest data from databases
- Streaming ingestion overview
- Stream data with HTTP API
- Stream data using Source Connectors
- Web SDK tutorials
- Mobile SDK tutorials
- Data Lifecycle
- Data Science Workspace
- Overview
- Architecture
- Load data in JupyterLab notebooks
- Query and discover data in JupyterLab notebooks
- Exploratory Data Analysis
- Recipes, models, and services overview
- Build a model using the recipe builder template
- Analyze model performance
- Create and publish a trained model (UI)
- Schedule automated training and scoring for a service
- Enrich Real-Time Customer Profiles with machine learning insights
- Package source files into a recipe
- Import a packaged recipe (UI)
- Import a packaged recipe (API)
- Destinations
- Destinations overview
- Connecting to destinations
- Create destinations and activate data
- Activate profiles and segments to a destination
- Configure a dataset export destination
- Integrate with Google Customer Match
- Configure the Azure Blob destination
- Configure the Marketo destination
- Configure file-based cloud storage or email marketing destinations
- Configure a social destination
- Activate through LiveRamp destinations
- Adobe Target and Custom Personalization
- Activate data to non-Adobe applications webinar
- Identities
- Intelligent Services
- Monitoring
- Partner data support
- Profiles
- Understanding Real-Time Customer Profile
- Profile overview diagram
- Bring data into Profile
- Customize profile view details
- View account profiles
- Create merge policies
- Union schemas overview
- Create a computed attribute
- Pseudonymous profile expirations (TTL)
- Delete profiles
- Update a specific attribute using upsert
- Privacy and Security
- Introduction to Privacy Service
- Identity data in Privacy requests
- Privacy JavaScript library
- Privacy labels in Adobe Analytics
- Getting started with the Privacy Service API
- Privacy Service UI
- Privacy Service API
- Subscribe to Privacy Events
- Set up customer-managed keys
- 10 considerations for Responsible Customer Data Management
- Elevating the Marketer’s Role as a Data Steward
- Queries
- Overview
- Query Service UI
- Query Service API
- Explore Data
- Prepare Data
- Adobe Defined Functions
- Data usage patterns
- Run queries
- Generate datasets from query results
- Tableau
- Analyze and visualize data
- Build dashboards using BI tools
- Recharge your customer data
- Connect clients to Query Service
- Validate data in the datalake
- Schemas
- Overview
- Building blocks
- Plan your data model
- Convert your data model to XDM
- Create schemas
- Create schemas for B2B data
- Create classes
- Create field groups
- Create data types
- Configure relationships between schemas
- Use enumerated fields and suggested values
- Copy schemas between sandboxes
- Update schemas
- Create an ad hoc schema
- Sources
- Use Case Playbooks
- Experience Cloud Integrations
- Industry Trends
Analyze model performance in Data Science Workspace
Learn about some of the different methods used to analyze the performance of a model such as a confusion matrix, Accuracy, Recall, and Precision. For more information, please visit the Data Science Workspace documentation.
Change language
Copyright © 2025 Adobe. All Rights Reserved.
