SOTAVerified

Feature Engineering

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.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1451–1460 of 1706 papers

TitleStatusHype
Drug-Drug Interaction Extraction from Biomedical Text Using Long Short Term Memory NetworkCode0
Deep Recurrent Neural Network for Protein Function Prediction from Sequence—0
Match-Tensor: a Deep Relevance Model for SearchCode0
An Empirical Analysis of Feature Engineering for Predictive ModelingCode0
Exploration of Proximity Heuristics in Length Normalization—0
Deep-HiTS: Rotation Invariant Convolutional Neural Network for Transient DetectionCode0
Learning Feature Engineering for Classification—0
Training End-to-End Dialogue Systems with the Ubuntu Dialogue Corpus—0
Graph Convolutional Networks for Named Entity RecognitionCode0
Sparse Coding of Neural Word Embeddings for Multilingual Sequence Labeling—0
Show:102550
← PrevPage 146 of 171Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CNN14 gestures accuracy0.98—Unverified