---
title: Model insights
description: Introduces the many insights the DataRobot Leaderboard provides when you select a model, with links to details.

---

# Model insights {: #model-insights }

When you select a model, DataRobot makes available a large selection of insights, grouped by purpose, appropriate for that model.

## Model Leaderboard {: #model-leaderboard }

The model Leaderboard is a list of models ranked by the chosen performance metric, with the best models at the top of the list. It provides a [variety of insight tabs](#leaderboard-tabs), available based on user permissions and applicability. Hover over an inactive division to view a dropdown of member tabs.

!!! note
    Tabs are visible only if they are applicable to the <i>project type</i>. For example, time series-related tabs (e.g., <b>Accuracy Over Time</b>) only display for time series projects. Tabs that are applicable to a project but not a particular <i>model type</i> display as grayed out (for example, [blender](leaderboard-ref#blender-models) models, due to the nature of their construction, have fewer tab functions available).

![](images/divisions.png)

The pages within this section provide information on using and interpreting the insights available from the Leaderboard (**Models** tab). See the [Leaderboard reference](leaderboard-ref) for information on the badges and components of the Leaderboard as well as functions such as tagging, searching, and exporting data.

## Leaderboard tabs {: #leaderboard-tabs }

|   Tab name    |  Description |
|---------------|--------------|
|**_[Evaluate](evaluate/index)_:** *Key plots and statistics for judging model effectiveness* | :~~:|
| [Accuracy Over Space](lai-insights)  | Provides a spatial residual mapping within an individual model. |
| [Accuracy over Time](aot)  | Visualizes how predictions change over time. |
| [Advanced Tuning](adv-tuning)  | Allows you to manually set model parameters, overriding the DataRobot selections. |
| [Anomaly Assessment](anom-viz) | Plots data for the selected backtest and provides SHAP explanations for up to 500 anomalous points. |
| [Anomaly over Time](anom-viz)  | Plots how anomalies occur across the timeline of your data. |
| [Confusion Matrix](multiclass)   | Compares actual data values with predicted data values in multiclass projects. For binary classification projects, use the [confusion matrix](confusion-matrix) on the [ROC Curve](roc-curve-tab/index) tab.|
| Feature Fit  | Removed. See [**Feature Effects**](feature-effects). |
| [Forecasting Accuracy](forecast-acc)  | Provides a visual indicator of how well a model predicts at each forecast distance in the project’s forecast window. |
| [Forecast vs Actual](fore-act)   | Compares how different predictions behave at different forecast points to different times in the future. |
| [Lift Chart](lift-chart)  | Depicts how well a model segments the target population and how capable it is of predicting the target. |
| [Residuals](residuals)  | Clearly visualizes the predictive performance and validity of a regression model. |
| [ROC Curve](roc-curve-tab/index)  | Explores classification, performance, and statistics related to a selected model at any point on the probability scale. |
| [Series Insights](series-insights-multi)  |  Provides series-specific information. |
|  [Stability](stability)  | Provides an at-a-glance summary of how well a model performs on different backtests. |
| [Training Dashboard](training-dash) | Provides an understanding about training activity, per iteration, for Keras-based models. |
| **_[Understand](understand/index):_** *Explains what drives a model’s predictions* | :~~:|
| [Feature Effects](feature-effects)  | Visualizes the effect of changes in the value of each feature on the model’s predictions.  |
| [Feature Impact](feature-impact)   | Provides a high-level visualization that identifies which features are most strongly driving model decisions.  |
| [Cluster Insights](cluster-insights) | Captures latent features in your data, surfacing and communicating actionable insights and identifying segments in your data for further modeling. |
| [Prediction Explanations](pred-explain/index)  | Illustrates what drives predictions on a row-by-row basis using XEMP or SHAP methodology. |
| [Word Cloud](analyze-insights#word-cloud-insights)  | Displays the most relevant words and short phrases in word cloud format.  |
| **_[Describe](describe/index):_** *Model building information and feature details* | :~~:|
| [Blueprint](blueprints)   | Provides a graphical representation of the data preprocessing and parameter settings via blueprint. |
| [Coefficients](coefficients)  | Provides, for select models, a visual representation of the most important variables and a coefficient export capability.|
| [Constraints](monotonic)  | Forces certain XGBoost models to learn only monotonic (always increasing or always decreasing) relationships between specific features and the target.  |
| [Data Quality Handling Report](dq-report) | Provides transformation and imputation information for blueprints. |
| [Eureqa Models](eureqa)  | Provides access to model blueprints for Eureqa generalized additive models (GAM), regression models, and classification models.  |
| [Log](log)  | Lists operation status results. |
| [Model Info](model-info)  | Displays model information. |
| [Rating Table](rating-table)  | Provides access to an export of the model’s complete, validated parameters. |
| **_[Predict](predictions/index.md)_:** *Access to prediction options* | :~~:|
| [Deploy](deploy-model)  | Creates a deployment and makes predictions or generates a model package. |
| [Downloads](download) | Provides export of a model binary file, validated Java Scoring Code for a model, or charts. |
| [Make Predictions](predict)  | Makes in-app predictions. |
| **_[Compliance](compliance/index)_:** *Compiles model documentation for regulatory validation* | :~~:|
| [Compliance Documentation](compliance) | Generates individualized model documentation.  |
| [Template Builder](template-builder)  | Allows you to create, edit, and share custom documentation templates. |
| **_[Comments](catalog-asset#add-comments)_:** *Adds comments to a modeling project* | :~~:|
| [Comments](catalog-asset#add-comments)| Adds comments to items in the **AI Catalog**. |
| **_[Bias and Fairness](bias/index)_:** *Tests models for bias* | :~~:|
| [Per-Class Bias](per-class) | Identifies if a model is biased, and if so, how much and who it's biased towards or against. |
| [Cross-Class Data Disparity](cross-data) | Depicts why a model is biased, and where in the training data it learned that bias from. |
| [Cross-Class Accuracy](cross-acc)  | Measures the model's accuracy for each class segment of the protected feature.  |
| **_[Insights and more](other/index)_:** *Graphical representations of model details* | :~~:|
| [Activation Maps](analyze-insights#activation-maps)   | Visualizes areas of images that a model is using when making predictions. |
| [Anomaly Detection](analyze-insights#anomaly-detection) | Lists the most anomalous rows (those with the highest scores) from the Training data.  |
| [Category Cloud](analyze-insights#category-clouds) | Visualizes relevancy of a collection of categories from summarized categorical features. |
|  [Hotspots](analyze-insights#hotspots) | Indicates predictive performance. |
| [Image Embeddings](analyze-insights#image-embeddings) | Displays a projection of images onto a two-dimensional space defined by similarity.  |
| [Text Mining](analyze-insights#text-mining) | Visualizes relevancy of words and short phrases. |
| [Tree-based Variable Importance](analyze-insights#tree-based-variable-importance)  | Ranks the most important variables in a model.   |
| [Variable Effects](analyze-insights#variable-effects)| Illustrates the magnitude and direction of a feature's effect on a model's predictions. |
| [Word Cloud](analyze-insights#word-clouds) | Visualizes variable keyword relevancy. |
| [Learning Curves](learn-curve) | Helps to determine whether it is worthwhile to increase dataset size. |
| [Speed vs Accuracy](speed) | Illustrates the tradeoff between runtime and predictive accuracy. |
| [Model Comparison](model-compare)   | Compares selected models by varying criteria. |
| [Bias vs Accuracy](bias-tab)  | Illustrates the tradeoff between predictive accuracy and fairness. |
