FEATURE ENGINEERING: HOW TO SELECT AND CREATE IMPORTANT FEATURES
DOI:
https://doi.org/10.5281/zenodo.20354979Keywords:
Feature Engineering, feature selection, feature creation, overfitting, data transformation, correlation, Lasso, machine learning, Pandas, Scikit-learn.Abstract
The article highlights the role and significance of the Feature Engineering process in enhancing the efficiency of machine learning models. It provides a detailed analysis of feature selection methods, including statistical (filtering), iterative (wrapper), and embedded techniques. Additionally, strategies for creating new features, data transformation, the importance of domain knowledge, and key libraries in the Python ecosystem (Pandas, Scikit-learn) are discussed. The conclusion emphasizes the prospects of automation in the field and the crucial role of expert intuition.References
Bishop, C. M. Pattern Recognition and Machine Learning. Springer, 2006. – pp. 173–186.
Guyon, I., & Elisseeff, A. An Introduction to Variable and Feature Selection. Journal of Machine Learning Research, 2003. – pp. 1157–1182.
Pedregosa, F., et al. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 2011. – vol. 12, pp. 2825–2830.
Kuhn, M., & Johnson, K. Feature Engineering and Selection: A Practical Approach for Predictive Models. CRC Press, 2019. – pp. 45–78.
Chollet, F. Deep Learning with Python. Manning Publications, 2018. – pp. 101–115.
Downloads
Published
2026-05-23
Issue
Section
Articles
License
Copyright (c) 2026 Innovative Academy RSC
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
Olimjonova, H., & Sobirjonov, B. (2026). FEATURE ENGINEERING: HOW TO SELECT AND CREATE IMPORTANT FEATURES. Science and Innovation, 4(45), 55-59. https://doi.org/10.5281/zenodo.20354979
Article metrics
Views and PDF downloads
1
Views
0
Downloads
