--- schema_version: "1" id: 9a6511685aa7be9508d22768da153e9fa75d588d5ef7fadf9728d46b41fec504 title: Detect and Remove Bias from a Model collection: admin version: current locale: en-us portal_url: https://docs.salesforce.com/admin/current/en-us/analytics/264-0-0/bi_edd_story_bias.md canonical_url: https://help.salesforce.com/s/articleView?id=analytics.bi_edd_story_bias.htm&release=264.0.0&type=5 source_site: help.salesforce.com content_type: documentation content_hash: 24201f8850b30eebd8789378ae2dc0e127fedb2186511426dfd23c018b13635a description: Einstein Discovery helps you practice ethical use of AI by detecting bias in your data so that you can remove its distorting effects on your analysis and predictions. Bias indicates that variables are being treated unequally in your model. products: - CRM Analytics - Cross Cloud release: "264" --- # Detect and Remove Bias from a Model Einstein Discovery helps you practice ethical use of AI by detecting bias in your data so that you can remove its distorting effects on your analysis and predictions. Bias indicates that variables are being treated unequally in your model. ### Required Editions ![Note](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-analytics-bi-264-0-0-production-enus/ec791473-f5b4-4f64-a656-9104f455d966/images/icon_note.png) Note Einstein Discovery stories are now models. We wish we could snap our fingers to update the name everywhere, but you can expect to see the previous name in a few places until we replace it.
Available in Salesforce Classic and Lightning Experience.
Available with CRM Analytics, which is available for an extra cost in Enterprise, Performance, and Unlimited Editions. Also available in Developer Edition.
Examples of bias include: - _Proxy variables_, where a variable is highly correlated to a sensitive variable, such as a loan applicant's street address and ethnicity. - _Disparate impact_ is a type of analysis we do to try to understand how different groups are being treated by the model. Einstein Discovery lets you flag data that could potentially be associated with unfair treatment—such as race, gender, religion, national origin, sexual orientation, disability, age—as sensitive variables. Einstein Discovery then displays a shield icon next to models and insights associated with sensitive variables as a reminder of possible bias while you investigate your data. Removing biased variables from your model can produce more ethical and accountable insights. For an overview, take the following Trailhead modules: - [Ethical Model Development with Einstein Discovery: Quick Look](https://trailhead.salesforce.com/content/learn/modules/ethical-model-development-in-einstein-discovery-quick-look) - [Responsible Creation of Artificial Intelligence](https://trailhead.salesforce.com/en/content/learn/modules/responsible-creation-of-artificial-intelligence) To detect and remove bias in your model: 1. In Model Setup, select a variable that you suspect can indicate bias, click the **Settings** tab in the right panel, and select **Analyze for Bias**. ![Flagging a variable as sensitive](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-analytics-bi-264-0-0-production-enus/ec791473-f5b4-4f64-a656-9104f455d966/bi/images/bi/bi_edd_story_bias_sensitive.png) 2. Click **Update Model** to create a new model version. 3. To filter the list so that it contains only insights associated with sensitive variables, click the shield button. ![Shield button to filter the insights list by sensitive fields](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-analytics-bi-264-0-0-production-enus/ec791473-f5b4-4f64-a656-9104f455d966/bi/images/bi/bi_edd_story_bias_shield2.png) The shield icon indicates that this insight is associated with a variable that has been flagged as sensitive. ![Shield icon, showing that an insight is associated with a sensitive variable](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-analytics-bi-264-0-0-production-enus/ec791473-f5b4-4f64-a656-9104f455d966/bi/images/bi/bi_edd_story_bias_shield_insight.png) 4. Select an insight card. - Einstein Discovery shows you a disparate impact analysis if there is a significant discrepancy in the way different classes are being treated by the model. ![Disparate impact threshold line and explanation](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-analytics-bi-264-0-0-production-enus/ec791473-f5b4-4f64-a656-9104f455d966/bi/images/bi/bi_edd_story_bias_disparate_impact.png) - Einstein Discovery shows you a potential bias analysis if it detects possible proxy variables. ![Disparate impact threshold line and explanation](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-analytics-bi-264-0-0-production-enus/ec791473-f5b4-4f64-a656-9104f455d966/bi/images/bi/bi_edd_story_bias_proxy_variables.png) 5. Click **Edit Model** to view model settings. Notice how Einstein displays the shield icon and the **Disparate Impact** data alert for the variable. ![Model setup screen, showing the shield icon and alert for a sensitive variable](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-analytics-bi-264-0-0-production-enus/ec791473-f5b4-4f64-a656-9104f455d966/bi/images/bi/bi_edd_story_bias_settings.png) 6. Investigate your model’s insights to help you decide whether to include a sensitive variable (because it serves your analysis), or to exclude it and remove its biased influence from the model. To remove a variable, simply disable it and click **Update Model** to create a new model version without it. ![Disabling a sensitive field to remove its bias from the model](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-analytics-bi-264-0-0-production-enus/ec791473-f5b4-4f64-a656-9104f455d966/bi/images/bi/bi_edd_story_bias_removed.png) #### See Also - [Disparate Impact Alert](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_data_alert_disparate_impact.htm&release=264.0.0&type=5 "Indicates that there is a significant discrepancy in the way different classes are being treated, which can signal bias.") - [Proxy Variable Alert](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_data_alert_proxy_variables.htm&release=264.0.0&type=5 "Indicates that one or more variables are highly correlated to a sensitive variable, which means that the variable serves as a proxy variable in your analysis, which can signal bias. For example, a loan applicant's street address can serve as a proxy for ethnicity. Bias can be reflected in adverse approval rates if an institution's lending practices are discriminatory.") - [Ethical AI in Einstein Discovery](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_ethical_ai.htm&release=264.0.0&type=5 "Einstein Discovery offers bias detection and model cards to help you practice ethical use of artificial intelligence (AI) in your business.")