# Predict a regression target

> Predict a regression target - Predict a regression target using a DataRobot application using a no-
> code application.

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 `2026-05-06T18:17:09.950708+00:00` (UTC).

## Primary page

- [Predict a regression target](https://docs.datarobot.com/en/docs/get-started/how-to/predict-regression.html): Full documentation for this topic (HTML).

## Sections on this page

- [Assets for download](https://docs.datarobot.com/en/docs/get-started/how-to/predict-regression.html#assets-for-download): In-page section heading.
- [Car fuel economy data](https://docs.datarobot.com/en/docs/get-started/how-to/predict-regression.html#car-fuel-economy-data): In-page section heading.
- [Define the target](https://docs.datarobot.com/en/docs/get-started/how-to/predict-regression.html#define-the-target): In-page section heading.
- [Set up the project](https://docs.datarobot.com/en/docs/get-started/how-to/predict-regression.html#set-up-the-project): In-page section heading.
- [Create an experiment](https://docs.datarobot.com/en/docs/get-started/how-to/predict-regression.html#create-an-experiment): In-page section heading.
- [Create an application and make a prediction](https://docs.datarobot.com/en/docs/get-started/how-to/predict-regression.html#create-an-application-and-make-a-prediction): In-page section heading.

## Related documentation

- [Get started](https://docs.datarobot.com/en/docs/get-started/index.html): Linked from this page.
- [How-tos](https://docs.datarobot.com/en/docs/get-started/how-to/index.html): Linked from this page.
- [Introduction to data analysis in DataRobot](https://docs.datarobot.com/en/docs/get-started/how-to/intro-to-eda.html): Linked from this page.
- [Start modeling setup](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.
- [Compare models](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/manage-experiments/compare-models.html): Linked from this page.
- [Evaluate with model insights](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/index.html): Linked from this page.
- [Create custom applications](https://docs.datarobot.com/en/docs/wb-apps/custom-apps/upload-custom-app.html): Linked from this page.

## Documentation content

This walkthrough uses machine learning to build an application that will use a predictive model to predict the fuel efficiency of a new car that has not yet been designed.
Because the model needs to predict a number, this is a regression problem.
The walkthrough describes how to frame, set up, evaluate, and interpret predictions for a continuous target.
It then creates an application that can be used to make predictions based on adding new data to the application.

## Assets for download

To follow this walkthrough, download the dataset that will be used below.

[Download dataset](https://datarobot-doc-assets.s3.us-east-1.amazonaws.com/cars2020.csv)

### Car fuel economy data

The dataset contains information about cars that have been designed and tested.
The data is from the EPA's Fuel Economy Guide for 2020.

Each row in this dataset represents information about a car, such as the make, model, drivetrain, and other specifications. The dataset is based on [public data](http://www.fueleconomy.gov/feg/epadata/20data.zip) from the [fueleconomy.gov](http://www.fueleconomy.gov/) website.

> [!NOTE] Dataset notice
> This dataset was cleaned and modified for use in this exercise.

The data is from vehicle testing done at the EPA National Vehicle and Fuel Emissions Laboratory and from vehicle manufacturers. The data dictionary for each field is [also public](http://www.fueleconomy.gov/feg/ws/index.shtml#vehicle).

### Define the target

The target is the fuel efficiency of the car, measured in miles per gallon (MPG).
Notice that this is a continuous variable (i.e.,a number) rather than a binary True/False or Yes/No, making this a regression problem.

The other columns contain information that will help us predict MPG.

## Set up the project

Follow the steps provided in the [Introduction to data analysis in DataRobot](https://docs.datarobot.com/en/docs/get-started/how-to/intro-to-eda.html) walkthrough to set up the project.
Use the `cars2020.csv` dataset in place of the dataset provided in the walkthrough.
Once the project is set up, continue on to create an experiment.

## Create an experiment

The steps in this section build an experiment that will help predict the fuel efficiency of the car, which is indicated by the `MPG` feature.

1. From the data view for the dataset, clickData actions > Start modeling.
2. In theSet up new experimentwindow, specifyMPGin theTarget featurefield. Also ensure that theTarget typeis set toRegression.
3. Leave the remaining fields at their defaults and clickNext >. NoteFor more details on the additional settings, seeStart modeling setup.
4. Leave all partitioning changes fields at their defaults and clickStart modeling. After a few moments, the Model Leaderboard appears and indicates the training progress. Model build timeModel build time can vary depending on the size of the dataset. When it completes, theWorkerspane displaysNo jobs currently running.
5. Once the models are built, the Model Leaderboard indicates the top model asPrepared for deployment. Click it to view the model's details.

For details on how to assess the various models after they are built, see [Compare models](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/manage-experiments/compare-models.html) and [Evaluate with model insights](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/index.html).

## Create an application and make a prediction

Now that the best model has been identified, it can be registered and deployed to a production environment for use in making predictions.
The steps below create an application that can be used to make predictions.

1. From the best model's details page, clickModel actions > Create a no-code application.
2. Once the application has been created, clickPredictionsin the left navigation pane.
3. The page refreshes to display all predictions data in the application. Scroll down to theSubmit Single Predictionsection and clickMake prediction.
4. In theAdd new predictionwindow, you can specify the features that should be used to make the new prediction. For this example, specify the values in the table below. FeatureValueDisplacement10Cylinders16TransmissionAuto(AM-S7)DriveAll wheel driveGears7Exhaust Valves Per Cyl2Intake Valves Per Cyl2Recommended FuelDieselModel Index121Max Ethanol10
5. ClickAdd prediction.
6. The new prediction is displayed in the first row of thePredictionssection. In this case, the predicted fuel efficiency is 11.152 MPG.

Repeat the steps above to generate additional predictions as needed.
If you would like to make multiple predictions at once, you can upload a CSV file with the predictions under the Batch Prediction section.

For additional details on how to create and work with custom applications, see [Create custom applications](https://docs.datarobot.com/en/docs/wb-apps/custom-apps/upload-custom-app.html).