# Run choice-based conjoint analysis

> Run choice-based conjoint analysis - Use conjoint analysis to identify customer preferences for
> product features through survey-based choice modeling and interpretability with DataRobot.

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 `2026-05-06T18:17:09.582404+00:00` (UTC).

## Primary page

- [Run choice-based conjoint analysis](https://docs.datarobot.com/en/docs/api/dev-learning/accelerators/model-deploy-mlops/conjoint.html): Full documentation for this topic (HTML).

## Related documentation

- [Developer documentation](https://docs.datarobot.com/en/docs/api/index.html): Linked from this page.
- [Developer learning](https://docs.datarobot.com/en/docs/api/dev-learning/index.html): Linked from this page.
- [AI accelerators](https://docs.datarobot.com/en/docs/api/dev-learning/accelerators/index.html): Linked from this page.
- [Model deployment and MLOps](https://docs.datarobot.com/en/docs/api/dev-learning/accelerators/model-deploy-mlops/index.html): Linked from this page.

## Documentation content

[Access this AI accelerator on GitHub](https://github.com/datarobot/data-science-scripts/blob/master/accelerators_dev/use_cases_and_horizontal_approaches/Choice-based-conjoint.ipynb)

Conjoint analysis is a tool widely used in marketing research for new product development testing. It's usually executed as an online survey format where a few survey respondents will make one choice out of a set of different alternatives. The output allows researches to accurately identify which product features and combination works best before developing them.

This notebook outlines how to run a choice-based conjoint analysis as part of the broader Conjoint Analysis topic, with the focus being on the modeling aspect to derive preference scores. DataRobot's SHAP values add the value of interpretability over traditional methods using a linear regression coefficient scores where negative coefficients make it hard to interpret.

From a technical perspective, conjoint analysis is a method to identify respondent (customer) preferences of a product feature, without explicitly asking them about that product feature in a survey. This is done by asking respondents to choose one item out of a set of alternatives. Each alternative is made up of the different feature combinations and permutations you are seeking to test. As you run the survey across a large number of responses, DataRobot helps identify customer latent/unconscious feature preferences, even those they themselves may not realize.