Creating Regression model
From a workbook, click Actions > ML Dashboard. The ML Dashboard page is displayed. From the Create Model section, click Regression and specify the following:
| Feature | Linear Regression |
|---|---|
| Model Type | Generalized linear model |
| Best Suited For | Linearly related continuous targets; when interpretability is key |
| Relationship Modeling | Assumes a linear relationship between predictors and target |
| Handling of Interactions | Requires manual inclusion of interaction terms |
| Interpretability | Very high – clear coefficient estimates and significance tests |
| Parameter Tuning | Minimal – primarily choice of regularization (e.g., L1/L2 penalties) |
| Data Requirements | Needs homoscedasticity, no multicollinearity, and normally distributed errors |
| Handling of Outliers | Sensitive to outliers; robust variants (e.g., RANSAC) can mitigate |
| Multicollinearity | Problematic – variance inflation; requires feature selection or PCA |
| Feature Importance | Directly from coefficient magnitudes |
| Library Support | scikit-learn (LinearRegression, Ridge, Lasso), statsmodels |
| Prediction Output | Continuous point estimates (with optional confidence intervals) |
| Deployment Readiness | Extremely lightweight; instantaneous inference; minimal memory footprint |
| External Features | New features simply added as new coefficients |
| Community & Resources | Extensive academic literature; ubiquitous baseline for regression tasks |
Click Create and commence the model training process.