TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Methodology/Feature Engineering

Feature Engineering

21 benchmarks1706 papers

Feature engineering is the process of taking a dataset and constructing explanatory variables — features — that can be used to train a machine learning model for a prediction problem. Often, data is spread across multiple tables and must be gathered into a single table with rows containing the observations and features in the columns.

The traditional approach to feature engineering is to build features one at a time using domain knowledge, a tedious, time-consuming, and error-prone process known as manual feature engineering. The code for manual feature engineering is problem-dependent and must be re-written for each new dataset.

Benchmarks

Feature Engineering on Beijing Multi-Site Air-Quality Dataset

MAE (PM2.5)

Feature Engineering on MuJoCo

MSE (10^2, 50% missing)

Feature Engineering on Basketball Players Movement

Path LengthOOB Rate (10^−3) Step Change (10^−3)Path DifferencePlayer Distance

Feature Engineering on PEMS-SF

L2 Loss (10^-4)

Feature Engineering on PhysioNet Challenge 2012

MAE (10% of data as GT)mse (10^-3)AUROC

Feature Engineering on UCI localization data

MAE (10% missing)

Feature Engineering on KDD CUP Challenge 2018

MSE (10% missing)

Feature Engineering on 2019_test set

14 gestures accuracy

Feature Engineering on Electricity

MAE (100 steps, 10% data missing)

Feature Engineering on HMNIST

AUROCMSENLL

Feature Engineering on METR-LA

1 step MAE

Feature Engineering on Sprites

MSE

Feature Engineering on Adult

Test error