May 1, 2024
Updated May 11, 2025
26 minute read
Feature selection is a critical process in the realm of data science and machine learning. At its core, it involves identifying and selecting the most relevant features, or variables, from a dataset to build predictive models. Imagine trying to describe an object using only its most defining characteristics; feature selection does something similar for data. This process is essential, especially when dealing with high-dimensional datasets where numerous features might not all contribute equally to the prediction.
si2y4k|
Find a path to becoming a Feature Selection. Learn more at:
OpenCourser.com/topic/si2y4k/feature
Reading list
We've selected 26 books
that we think will supplement your
learning. Use these to
develop background knowledge, enrich your coursework, and gain a
deeper understanding of the topics covered in
Feature Selection.
Provides a dedicated and in-depth exploration of feature selection specifically within the context of knowledge discovery and data mining. It covers theoretical aspects and various techniques, making it a valuable resource for researchers and advanced practitioners in the field.
Focused specifically on feature selection techniques implemented in Python, this book provides practical code examples and explanations. It is particularly useful for those who want to apply feature selection methods using popular Python libraries. is well-suited for undergraduate students and practitioners seeking a code-centric approach.
Covering the entire predictive modeling process, this book includes important sections on data preprocessing and feature selection. It offers practical advice and examples, making it a useful resource for practitioners and students interested in building effective predictive models. It can serve as a textbook or a comprehensive reference.
A comprehensive and foundational text in statistical learning, this book covers various topics including model selection and regularization, which are closely related to feature selection. While mathematically rigorous, it provides deep theoretical insights. It classic reference for graduate students and researchers.
Delves into various computational methods used for feature selection. It is likely to cover a wide range of algorithms and their computational aspects. This book would be suitable for graduate students and researchers interested in the algorithmic details of feature selection.
Focuses on statistical learning methods that induce sparsity, such as the Lasso, which inherently perform feature selection by shrinking coefficients of irrelevant features to zero. It provides a deeper understanding of these embedded methods.
Focuses on the principles and techniques of feature engineering, a closely related field to feature selection. It provides practical methods for creating and transforming features, which is crucial before applying feature selection. It's a good resource for data scientists looking to improve their data preparation skills.
A classic and foundational text in the field of pattern recognition. It covers fundamental concepts related to feature extraction and selection, providing historical context and theoretical basis for many modern techniques. Essential reading for those seeking a deep understanding of the origins of these methods.
This widely-respected textbook covers fundamental concepts in pattern recognition and machine learning from a probabilistic perspective. It includes discussions on dimensionality reduction and model comparison, providing essential background for understanding feature selection within a broader ML context. It is suitable for advanced undergraduates and graduate students.
This textbook provides a solid foundation in machine learning, including coverage of feature engineering and selection as part of the machine learning pipeline. It balances theoretical concepts with practical applications, making it suitable for advanced undergraduates and graduate students seeking a comprehensive understanding.
This comprehensive machine learning textbook includes coverage of dimensionality reduction and feature selection techniques as part of the broader ML landscape. It offers a balanced view of theoretical concepts and practical algorithms, suitable for undergraduate and graduate students.
A widely used introductory textbook on machine learning that covers essential topics including dimensionality reduction and feature selection. It provides a solid foundation in the core concepts of ML and the importance of feature preprocessing.
This practical book focuses on feature engineering techniques, including methods for selecting features. It provides a hands-on approach with code examples, making it accessible for beginners and those looking to quickly apply techniques. Useful for undergraduates and those starting in data science.
Though this book focuses on the broader topic of feature engineering, it includes a chapter on feature selection.
While focused on time series forecasting, the latest edition of this book includes a chapter on time series features, which is directly relevant to feature engineering and selection in time series data. It's a valuable resource for those working with sequential data.
A practical guide to feature selection using the R programming language.
While primarily about dimensionality reduction, this book has a chapter on feature selection.
An accessible introduction to feature selection techniques.
For more information about how these books relate to this course, visit:
OpenCourser.com/topic/si2y4k/feature
Save
