Explainable AI Model for Recognizing Financial Crisis Roots Based on Pigeon Optimization and Gradient Boosting Model

Abstract

Utilizing Artificial Intelligence (AI) techniques to forecast, recognize, and classify financial crisis roots are important research challenges that have attracted the interest of researchers. Moreover, the Explainable Artificial Intelligence (XAI) concept enables AI techniques to interpret the results of processing and testing complex data patterns so that humans can find efficient ways to infer and interpret the logic behind classifying complex data patterns. This paper proposes a novel XAI model to automatically recognize financial crisis roots and interprets the features selection operation. Using a benchmark dataset, the proposed XAI model utilized the pigeon optimizer to optimize the feature selection operation, and then the Gradient Boosting classifier is utilized to recognize financial crisis roots based on the obtained reduct of the most important features. The practical results showed that the short-term interest rates feature is the most important feature by which financial crisis roots can be detected. Moreover, the classification results showed that the built-in Gradient Boosting classifier in the Pigeon Inspired Optimizer (PIO) algorithm achieved training and testing accuracy of 99% and 96.7%, respectively, in recognizing financial crisis roots, which is an efficient and better performance compared to the random forest classifier.