CSI Score uses Einstein Studio's Gradient Boosting Machine (GBM) to identify the top-drivers for the composite scores. Each composite score gets its unique predictive model. You can retrain the models with your company's data and modify the models to include KPIs unique to your company.
- Understand How Predictive Models Work in CSI Score
Before you start working with predictive models for CSI Score, learn about the predictive modeling assets of CSI Score installed in your org. Know the predictive modeling tasks completed during CSI Score installation and review AI Models resources to learn about predictive modeling in Data 360. - Train Predictive Model with Customized CSI Score Semantic Model
During CSI Score installation, the predictive models are trained automatically with synthetic data. This training doesn't consider any company-specific nuances, such as additional KPIs or updates to composite score calculation logic. After your company's custom CSI Score semantic model is ready with company-specific scores, weights, and formulas, retrain the predictive models with actual data. And set a training schedule for the updated models. - Predictive Model Customization Use Case Library for CSI Score
Learn about the various types of business use cases that you can achieve by customizing the predictive models of CSI Score.