ABSTRACT
This chapter gives a brief overview of the basic ideas and ALD uses of feature engineering in machine learning-based learning, it is crucial to recognize that the subject is wide and constantly evolving. It examines the diverse techniques of machine-learning based feature engineering and its significance in reducing the dimensions of data, identify and extract irrelevant information and select the most appropriate variables which influences thin film qualities. According to some scholars, the primary goal of feature engineering is to ease the curse of dimensionality brought on by the data's rapid evolution. Other researchers opined that the primary goal of feature engineering is to improve machine learning by optimizing the feature space representation. Since scaling reduces variability, the feature transformation technique lessens the impact of outliers. By focusing on the most crucial elements that influence the model's forecast accuracy, the authors may narrow our attention.
