Music Genre Classification Using Machine Learning (XGBoost): A Systematic Review

The evolution of music genre classification, driven by advancements in machine learning, has revolutionized the way we organize and categorize music. Historically relying on cultural and regional characteristics, modern classification systems face the challenge of accommodating the diverse array of digital music genres. This paper reviews recent studies in music genre classification, focusing on the effectiveness of XGBoost and other machine learning algorithms. Despite challenges like limited datasets and the absence of lyrical data, XGBoost has shown promising results. However, future research should explore hybrid models and address data diversity challenges for more precise classification. Collaboration across disciplines is crucial for innovation in this interdisciplinary field.