--- schema_version: "1" id: e3dbbd73fedca596d8ced5549b50533deb95829783027a241681909a67e26f00 title: Understand the Data That Einstein Uses collection: admin version: current locale: en-us portal_url: https://docs.salesforce.com/admin/current/en-us/mktg/264-0-0/mc_anb_einstein_and_data.md canonical_url: https://help.salesforce.com/s/articleView?id=mktg.mc_anb_einstein_and_data.htm&release=264.0.0&type=5 source_site: help.salesforce.com content_type: documentation content_hash: 14001cd636dac9adde594d22129402a92cf78ed6f128b3b67c1289ea1183b901 description: Providing Einstein with good data makes it more likely to get good predictions. For Einstein predictive features, use data quality scores to understand the quality of the data that each Einstein app requires to generate predictions, insights, analytics, and more. Find data quality metrics on each Einstein app dashboard and Einstein Overview card. products: - Marketing - Marketing Cloud Intelligence release: "264" --- # Understand the Data That Einstein Uses Providing Einstein with good data makes it more likely to get good predictions. For Einstein predictive features, use data quality scores to understand the quality of the data that each Einstein app requires to generate predictions, insights, analytics, and more. Find data quality metrics on each Einstein app dashboard and Einstein Overview card. ## Considerations - Achieving a 100% data quality score isn’t the objective. Instead, use your current score as a benchmark for future results. When your data score is above the minimum threshold, you’re likely to see benefits from AI. - The longer Einstein is enabled and learning, the better your results are likely to be. Each Einstein app is unique, but most apps can deliver results within 90 days. - AI works best when it has lots of data to analyze. Using global data models for predictive apps boosts the amount of data used for making predictions. Global models safely harness the power of Salesforce to provide more accurate, actionable results. Transactional sends and test sends are excluded when generating your data quality score. ## Related Content


	Einstein Generative AI & Trust
	Einstein Trust Layer
	Generative AI Basics
	Artificial Intelligence Fundamentals

- **[Einstein and Data Usage in Marketing Cloud Engagement](https://help.salesforce.com/s/articleView?id=mktg.mc_anb_einstein_features_data_usage_marketing_cloud.htm&release=264.0.0&type=5)** Einstein is built on data. When using Marketing Cloud Engagement, review this table to understand the type of data used by Einstein features. - **[Global Model Data Opt In and Opt Out in Marketing Cloud Engagement](https://help.salesforce.com/s/articleView?id=mktg.mc_anb_einstein_sto_global_data_model.htm&release=264.0.0&type=5)** Einstein intelligence is built on data. The more data Einstein has, the more powerful the resulting predictions. Most organizations don’t have enough data to build their own models. To give you more meaningful predictive AI, Salesforce builds global predictive models that scan for aggregate, anonymous trends across many Salesforce customers. To protect your customer data, your account is opted out of the global data model by default. - **[Gauge Your Einstein Engagement Scoring Data Quality](https://help.salesforce.com/s/articleView?id=mktg.mc_anb_einstein_ees_data_quality.htm&release=264.0.0&type=5)** Check your mobile app’s data quality score for insight about the engagement data that Einstein uses to predict your customers’ likelihood to engage. Data quality scores for Einstein Engagement Scoring are generated at the mobile app level only. - **[Data Residency](https://help.salesforce.com/s/articleView?id=mktg.mc_anb_data_residency_hyperforce.htm&release=264.0.0&type=5)** Hyperforce is the next-generation Salesforce infrastructure architecture that gives you more choice and control over data residency. If your organization in Australia, Canada, India, and Japan uses Hyperforce, Einstein can process data outside your geographical location. The United States and Europe maintain data residency in their local region.