# Predictive workflow overview

> Predictive workflow overview - A generalized discussion of the steps to build predictive models in
> Workbench.

This Markdown file sits beside the HTML page at the same path (with a `.md` suffix). It summarizes the topic and lists links for tools and LLM context.

Companion generated at `2026-05-06T18:17:09.942565+00:00` (UTC).

## Primary page

- [Predictive workflow overview](https://docs.datarobot.com/en/docs/get-started/day0/predai-start/pred-workflow.html): Full documentation for this topic (HTML).

## Sections on this page

- [Predictive model training workflow](https://docs.datarobot.com/en/docs/get-started/day0/predai-start/pred-workflow.html#predictive-model-training-workflow): In-page section heading.
- [Analyze and select a model](https://docs.datarobot.com/en/docs/get-started/day0/predai-start/pred-workflow.html#analyze): In-page section heading.
- [Which visualizations should you use?](https://docs.datarobot.com/en/docs/get-started/day0/predai-start/pred-workflow.html#which-visualizations-should-you-use): In-page section heading.

## Related documentation

- [Get started](https://docs.datarobot.com/en/docs/get-started/index.html): Linked from this page.
- [First time here?](https://docs.datarobot.com/en/docs/get-started/day0/index.html): Linked from this page.
- [Start with predictive modeling](https://docs.datarobot.com/en/docs/get-started/day0/predai-start/index.html): Linked from this page.
- [fundamentals of predictive modeling](https://docs.datarobot.com/en/docs/get-started/day0/predai-start/pred-fundamentals.html): Linked from this page.
- [import your data](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/dataprep/add-data/index.html): Linked from this page.
- [wrangle your data](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/dataprep/wrangle-data/index.html): Linked from this page.
- [exploratory data analysis](https://docs.datarobot.com/en/docs/reference/data-ref/eda-explained.html): Linked from this page.
- [target](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/create-experiments/create-predictive/ml-basic-experiment.html#start-modeling-setup): Linked from this page.
- [feature lists](https://docs.datarobot.com/en/docs/classic-ui/modeling/build-models/build-basic/feature-lists.html): Linked from this page.
- [feature importance](https://docs.datarobot.com/en/docs/reference/pred-ai-ref/model-ref.html#importance-score): Linked from this page.
- [feature engineering](https://docs.datarobot.com/en/docs/classic-ui/data/transform-data/index.html): Linked from this page.
- [blueprints](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/model-blueprint.html): Linked from this page.
- [Leaderboard](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/manage-experiments/leaderboard.html): Linked from this page.
- [optimization metric](https://docs.datarobot.com/en/docs/classic-ui/modeling/build-models/build-basic/model-data.html#optimization-metric): Linked from this page.
- [model comparison](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/manage-experiments/compare-models.html): Linked from this page.
- [rerunning modeling](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/manage-experiments/experiment-add.html): Linked from this page.
- [send it to Registry](https://docs.datarobot.com/en/docs/workbench/nxt-registry/index.html): Linked from this page.
- [test predictions](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/make-predictions.html): Linked from this page.
- [make predictions](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-predictions/nxt-make-predictions.html): Linked from this page.
- [set up a recurring batch prediction job](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-predictions/nxt-prediction-jobs.html#schedule-recurring-batch-prediction-jobs): Linked from this page.
- [monitor](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-monitoring/index.html): Linked from this page.
- [automatic retraining](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-mitigation/nxt-retraining.html): Linked from this page.
- [challenger models](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-mitigation/nxt-challengers.html): Linked from this page.
- [full list of insights](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/index.html): Linked from this page.
- [Feature Impact](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/feature-impact.html): Linked from this page.
- [Feature Effects](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/feature-effects.html): Linked from this page.
- [Individual Prediction Explanations](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/shap-predex.html): Linked from this page.
- [Lift Chart](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/lift-chart.html): Linked from this page.
- [Residuals plot](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/residuals.html): Linked from this page.
- [ROC Curve](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/roc-curve.html): Linked from this page.
- [Confusion Matrix (binary experiments)](https://docs.datarobot.com/en/docs/classic-ui/modeling/analyze-models/evaluate/roc-curve-tab/confusion-matrix-classic.html): Linked from this page.
- [Confusion Matrix (multiclass experiments)](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/confusion-matrix.html): Linked from this page.
- [Accuracy Over Time](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/aot.html): Linked from this page.
- [Forecast vs Actual](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/fcast-v-actual.html): Linked from this page.
- [Forecasting Accuracy](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/fcast-accuracy.html): Linked from this page.
- [Stability](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/stability.html): Linked from this page.
- [Series Insights](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/series-insights.html): Linked from this page.
- [Segmentation tab](https://docs.datarobot.com/en/docs/classic-ui/modeling/time/ts-segmented.html#leaderboard-model-scores): Linked from this page.
- [Metric values](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/multilabel.html): Linked from this page.
- [Image Embeddings](https://docs.datarobot.com/en/docs/classic-ui/modeling/special-workflows/visual-ai/vai-insights.html#image-embeddings): Linked from this page.
- [Neural Network Visualizer](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/neural-net.html): Linked from this page.
- [Word Cloud](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/word-cloud.html): Linked from this page.
- [Text Mining](https://docs.datarobot.com/en/docs/classic-ui/modeling/analyze-models/other/analyze-insights.html#text-mining): Linked from this page.
- [Anomaly Over Space](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/anom-over-space.html): Linked from this page.
- [Accuracy Over Space](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/acc-over-space.html): Linked from this page.
- [Cluster Insights](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/cluster-insights.html): Linked from this page.
- [Attention Maps](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/attention-map.html): Linked from this page.
- [Anomaly Over Time](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/anom-over-time.html): Linked from this page.
- [Anomaly Assessment](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/anom-assessment.html): Linked from this page.

## Documentation content

This section provides a generalized discussion of the steps to build predictive models in Workbench. See the [fundamentals of predictive modeling](https://docs.datarobot.com/en/docs/get-started/day0/predai-start/pred-fundamentals.html) for a description of predictive modeling methods.

## Predictive model training workflow

This section walks you through the steps to implement a DataRobot modeling experiment.

1. To begin the modeling process,import your dataorwrangle your datato provide a seamless, scalable, and secure way to access and transform data for modeling.
2. DataRobot conducts the first stage ofexploratory data analysis, (EDA1), where it analyzes data features. When registration is complete, theData previewtab shows feature details, including a histogram and summary statistics.
3. Next, for supervised modeling,select yourtargetand optionally change any other basic or advanced experiment configuration settings. Then,start modeling. DataRobot generatesfeature listsfrom which to build models. By default, it uses the feature list with the most informative features. Alternatively, you can select different generated feature lists orcreate your own.
4. DataRobot further evaluates the data during EDA2, determining which features correlate to the target (feature importance) and which features are informative, among other information. The application performsfeature engineering—transforming, generating, and reducing the feature set depending on the experiment type and selected settings.
5. DataRobot selectsblueprintsbased on the experiment type and builds candidate models.

## Analyze and select a model

DataRobot automatically generates models and displays them on the [Leaderboard](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/manage-experiments/leaderboard.html). The most accurate model is selected and trained on 100% of the data and is marked with the Prepared for Deployment badge.

To analyze and select a model:

1. Compare models by selecting anoptimization metricfrom theMetricdropdown.
2. Analyze the model using the visualization tools that are best suited for the type of model you are building. Usemodel comparisonfor experiments within a single Use Case. See thelist of experiment types and associated visualizationsbelow.
3. Experiment with modeling settings to potentially improve the accuracy of your model. You can tryrerunning modelingusing a different feature list or modeling mode.
4. After analyzing your models, select the best andsend it to Registryto create a deployment-ready model package. TipIt's recommended that youtest predictionsbefore deploying. If you aren't satisfied with the results, you can revisit the modeling process and further experiment with feature lists and optimization settings. You might also find that gathering more informative data features can improve outcomes.
5. As part of the deployment process, youmake predictions. You can alsoset up a recurring batch prediction job.
6. DataRobot uses a variety of metrics tomonitoryour deployment. Use the application's visualizations to track data (feature) drift, accuracy, bias, service health, and many more. You can set up notifications so that you are regularly informed of the model's status. TipConsider enablingautomatic retrainingto automate an end-to-end workflow. With automatic retraining, DataRobot regularly testschallenger modelsagainst the current best model (thechampion model) and replaces the champion if a challenger outperforms it.

## Which visualizations should you use?

Model insights help to interpret, explain, and validate what drives a model’s predictions. They are then used to assess what to do in your next experiment. While there are many visualizations available, not all are applicable to all modeling experiments—the visualizations you can access depend on your experiment type. The following table lists experiment types and examples of visualizations that are suited to their analysis. See the [full list of insights](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/index.html) to learn what you can access from your experiment's Leaderboard.

| Experiment type | Analysis tools |
| --- | --- |
| All models | Feature Impact: Provides a high-level visualization that identifies which features are most strongly driving model decisions.Feature Effects: Visualizes the effect of changes in the value of each feature on the model’s predictions.Individual Prediction Explanations: Illustrates what drives predictions on a row-by-row basis, answering why a given model made a certain prediction. |
| Regression | Lift Chart: Shows how well a model segments the target population and how capable it is of predicting the target. Residuals plot: Depicts the predictive performance and validity of a regression model by showing how linearly your models scale relative to the actual values of the dataset used. |
| Classification | ROC Curve: Explores classification, performance, and statistics related to a selected model at any point on the probability scale. Confusion Matrix (binary experiments): Compares actual data values with predicted data values in binary experiments.Confusion Matrix (multiclass experiments): Compares actual data values with predicted data values in multiclass experiments. |
| Time-aware modeling (time series and out-of-time validation) | Accuracy Over Time: Visualizes how predictions change over time.Forecast vs Actual: Compares how different predictions behave at different forecast points to different times in the future.Forecasting Accuracy: Provides a visual indicator of how well a model predicts at each forecast distance in the experiment’s forecast window.Stability: Provides an at-a-glance summary of how well a model performs on different backtests.Over Time chart: Identifies trends and potential gaps in your data by visualizing how features change over the primary date/time feature. The feature-over-time histogram displays once you select the ordering feature. |
| Multiseries | Series Insights: Provides a histogram and table for series-specific information. |
| Segmented modeling | Segmentation tab: Displays data about each segment of a Combined Model. |
| Multilabel modeling | Metric values: Summarizes performance across labels for different values of the prediction threshold (which can be set from the page). |
| Image augmentation | Image Embeddings: Projects images in two dimensions to see visual similarity between a subset of images and help identify outliers. Attention Maps: Highlights regions of an image according to its importance to a model's prediction.Neural Network VisualizerView a visual breakdown of each layer in the model's neural network. |
| Text AI | Word Cloud: Visualizes variable keyword relevancy.Text Mining: Visualizes relevancy of words and short phrases. |
| Geospatial AI | Anomaly Over Space: Displays anomalous score values on a unique map based on the validation partition. Accuracy Over Space: Provides a spatial residual mapping within an individual model. |
| Clustering | Cluster Insights: Captures latent features in your data, surfacing and communicating actionable insights and identifying segments for further modeling. [Image Embeddings]/ml-image-embeddings){ target=_blank }: Displays a experimention of images onto a two-dimensional space defined by similarity. Attention Maps: Visualizes areas of images that a model is using when making predictions. |
| Anomaly detection | Anomaly Over Time: Plots how anomalies occur across the timeline of your data . Anomaly Assessment: Plots data for the selected backtest and provides SHAP explanations for up to 500 anomalous points. |