Interpretable Automated Feature Engineering: A Comprehensive Review with a Focus on Dynamic and Stationary Environments

This paper presents a comprehensive review of Automated Feature Engineering (AFE) methods, with a focus on their application in static data environments and explores recent advancements in dynamic Feature Engineering (FE) for evolving data contexts. AFE is essential in modern Machine Learning (ML) pipelines, as it addresses the drawbacks of traditional FE, which often relies heavily on domain expertise and is labor intensive. By automating this process, AFE has the potential to enhance the efficiency, performance, and interpretability of ML workflows. The paper analyzes the methods, strengths, and limitations of different AFE methods. The review also identifies critical research gaps and proposes directions for future advancements. This work serves as a foundational resource for researchers aiming to optimize ML performance through novel AFE strategies.