Bias detection
Domino Integrated Model Monitoring detects and records traffic, drift, and health trends for all production models with out-of-the-box and custom metrics. The right people are notified at the right time when drift, divergence, and data quality checks exceed thresholds. When retraining is needed, it is easy to drill down into model features and quickly modify, retrain, and redeploy models.
Continuous fairness monitoring
Identifies model drift and potential biases in predictions.
Explainability tools
Uses SHAP values, LIME, and other techniques to ensure AI/ML models are interpretable.
Bias mitigation strategies
Enables proactive detection and correction of biases in applications like credit scoring, fraud detection, and risk assessments.
Related case studies
Saving Allstate countless hours
Allstate's team was losing precious time recreating models. With Domino, it can channel that time into creating value instead.
Empowering Direct Line's agents
Direct Line’s agents can focus on supporting customers when it matters most, using an AI model built on Domino.
Keeping BNP Paribas Cardif compliant
Cardif can process vital documents quickly and securely, with generative AI powered by the Domino Enterprise AI Platform.
Enabling governed AI innovation at USAA
To help it innovate safely, USAA created a solution to manage and purge experimental data sets.