Explainable Machine Learning Pipeline

Explainable Machine Learning (ML) pipelines aim to create AI systems whose decision-making processes are transparent and understandable, addressing the "black box" problem of many complex models. Current research focuses on developing both model-agnostic and intrinsic methods, employing techniques like genetic algorithms, Cartesian Genetic Programming, and LightGBM to build interpretable models and optimize pipeline design, often incorporating feature selection for enhanced explainability. This work is significant because it fosters trust and allows for better understanding and debugging of ML models across diverse applications, from drug design to image analysis and natural language processing.