Feature Engineering

Feature engineering is a preprocessing step in supervised machine learning and statistical modeling that transforms raw data into a more effective set of input features through selection, transformation, and derivation to enhance model predictive performance and interpretability.

79.2K

Publications

5.4M

Citations

170.6K

Authors

12.1K

Institutions

Publications per year

2017–2026

44.7K

Authors

170.6K

  1. DT
    Dacheng Tao

    The University of Sydney, Australia

    163 publications · 17.7K citations

    68

    h-index

  2. YY
    Yi Yang

    University of Technology Sydney, Australia

    122 publications · 25.8K citations

    68

    h-index

  3. FN
    Feiping Nie

    Northwestern Polytechnical University, China

    149 publications · 15.1K citations

    64

    h-index

  4. XW
    Xiaogang Wang

    European Organization for Nuclear Research, Switzerland

    94 publications · 29.8K citations

    64

    h-index

  5. DZ
    David Zhang

    Hong Kong Polytechnic University, Hong Kong SAR China

    137 publications · 19.1K citations

    62

    h-index

1–5 of 170.6K

Venues

  1. arXiv (Cornell University)

    Repository · 3.2K publications · 270.5K citations

    202

    h-index

  2. IEEE Transactions on Pattern Analysis and Machine Intelligence

    TPAMI · 694 publications · 200K citations

    187

    h-index

  3. IEEE Transactions on Image Processing

    886 publications · 96.7K citations

    155

    h-index

  4. Pattern Recognition

    969 publications · 89.5K citations

    136

    h-index

  5. IEEE Access

    2.1K publications · 107K citations

    133

    h-index

1–5

See also

Feature Engineering

Core Methods

Evaluation

Applications

Limitations

Automation