Understanding the Decision-Making Process of Music Genre Classification with Explainable Algorithms

Music genre classification is a fundamental task in music information retrieval, but the lack of interpretability in many machine learning models poses a significant challenge.To address this issue, we propose using a Random Forest Classifier (RFC), a simple and explainable artificial intelligence (XAI) technique, for music genre classification.Our objective is to develop a model that can identify the genre of a given music sample based on its audio features, while also providing insights into which features are most important for each genre.By doing so, we aim to gain a deeper understanding of the underlying patterns in music data and enable the development of more effective music-related applications.In this study, we combine two datasets and employ XAI techniques to gain insights into the decision-making process of the model while addressing the issue of class imbalance in the dataset.Overall, our approach provides a comprehensive and effective solution to music genre classification using XAI tools and methods.