Abstract: This presentation consists of showing the study developed in the paper “A Music Classification Model based on Metric Learning Applied to MP3 Audio Files” and the results obtained with the evolution of the study. This paper proposes a novel music classification model based on metric learning, whose main objective is to learn a personalized metric for each customer. The metric learning process considers the learning of a set of parameterized distances employing a structured prediction approach from a set of MP3 audio files containing several music genres according to the customer’s preference. To extract the acoustic information from audio files, we used the Mel-Frequency Cepstral Coefficient (MFCC) and made a dimensionality reduction using Principal Components Analysis (PCA). We attest to the model validity performing a set of experiments and comparing the results with Soft Margin Linear Support Vector Machine (SVM) .