NOTICE
The upcoming release of Featuretools 1.0.0 contains several breaking changes. Users are encouraged to test this version prior to release by installing from GitHub:
pip install https://github.com/alteryx/featuretools/archive/woodwork-integration.zip
For details on migrating to the new version, refer to Transitioning to Featuretools Version 1.0. Please report any issues in the Featuretools GitHub repo or by messaging in Alteryx Open Source Slack.
New projects are regularly being built on top of Featuretools, highlighting the importance of automated feature engineering. On this page, we have a list of libraries, use cases / demos, and tutorials that leverage Featuretools. If you would like to add a project, please contact us or submit a pull request on GitHub.
Note
We are proud and excited to share the work of people using Featuretools, but we cannot endorse or provide support for the tools on this page.
MLBlocks is a simple framework for composing end-to-end tunable Machine Learning Pipelines by seamlessly combining tools from any python library with a simple, common and uniform interface. MLBlocks contains a primitive that uses Featuretools.
Cardea is a machine learning library built on top of the FHIR data schema. It uses a number of automl tools, including Featuretools.
A common use case for machine learning is to predict customer lifetime value. This article walks through the importance of this prediction problem using Featuretools in the process.
Many users of Kaggle are eager to use Featuretools to improve their model performance. In this blog post, a Kaggle user takes a dataset of plays from National Hockey League games and creates a model to predict if a game is a playoff match.
Social programs have a difficult time determining the right people to give aid. Using a dataset of Costa Rican household characteristics, this Kaggle kernel predicts the poverty of households.
This notebook and accompanying report evaluates the use of machine learning for predicting a cyclist’s FTP using data collected from previous training sessions. Featuretools is used to generate a set of independent variables that capture changes in performance over time.
For more demos written by Feature Labs, see featuretools.com/demos
This article provides a walk-through of how to use a retail dataset with DFS.
A in-depth tutorial that works through using Featuretools to predict future product sales at “BigMart”.
A walk-through that applies Featuretools to a sample dataset and creates a classifier to predict clients who make large orders.
This article demonstrates using Featuretools helps automate the manual process of feature engineering on a dataset of home loans.
An automated feature engineering workshop using Featuretools hosted at the 2017 Data Summer Conference.
A tutorial of Featuretools that demonstrates integrating with the feature selection library Boruta and the hyper parameter tuning library Optuna.
A video tutorial that shows how to build a churn prediction model using Featuretools along with Spark, XGBoost, and Google Cloud Platform.
A video tutorial that shows how to predict if an applicant is capable of repaying a loan using Featuretools.