FEATURE ENGINEERING IN MACHINE LEARNING : SELECTION, EXTRACTION, AND THEIR IMPACT ON MODEL PERFORMANCE
Keywords:
extraction, distracting, unstructuredAbstract
In the data pre-processing stage of machine learning (ML), feature selection and extraction are
essential procedures. The models' computational efficiency, interpretability, and performance are all
greatly impacted by these stages. Finding the most relevant characteristics in a dataset while
maintaining important information is known as feature selection. However, in order to facilitate more
efficient learning, feature extraction converts unstructured data into meaningful representations. The
present work offers a thorough review of feature selection and extraction, emphasizing its
significance, different approaches, and applications in a range of fields. The research also highlights
issues like the Curse of Dimensionality, the existence of distracting or noisy characteristics, and the
efficacy being limited by the trade-off between interpretability and performance. In order to improve
scalability and cross-domain adaptation, the research finishes with insights into new trends and
potential paths, such as hybrid techniques and the combination of feature selection with deep
learning