Classification of Feature Engineering Techniques for Machine Learning under the Environment of Lattice Ordered T-Bipolar Soft Rings

The practice of adding new features or changing current features to enhance a machine-learning model’s performance is known as feature engineering. It increases the prediction potential of machine learning and aids in revealing the data’s underlying patterns. Different soft structures can be utilized to reach a decision where we have to decide the best alternative among the given choices. The structure of a ring is an algebraic structure that plays a vital role due to its characteristics. Moreover, a soft set is a valuable structure that can consider the parameterization tool. Also T-bipolar soft set is a parameterization tool that can consider the positive and negative aspects. Based on these observations we have developed the theory of lattice-ordered T-bipolar soft rings (LOTBSRs) and anti-lattice-ordered T-bipolar soft rings (ALOTBSRs). Moreover, we have defined the notions of OR product, extended union, and restricted union for LOTBSRs. Furthermore, the ideas of AND product, restricted intersection, and extended intersection are defined. To analyze the whole theory, we have proved some results related to these ideas. To construct the applications part of these developed notions, we have defined an algorithm and utilized these ideas in the decision-making scenarios for the classification of feature engineering techniques. In the end, we have some conclusion remarks.