<p>In this study, we proposed a similar music–recommendation method based on the baseline method. A similar music recommendation method using the Spotify API was proposed as a music retrieval method. The baseline method computes the Euclidean distance between the audio features obtained from the Spotify API. In this method, the normalization of the obtained audio features and validation of the features used were insufficient. Therefore, in this study, to confirm the effectiveness of music recommendation methods, a questionnaire is used as comparative data. From the results of the questionnaire, a ranking of each music is determined. To recommend music that is closer to the ranking, we propose a method to improve the baseline method. The proposed method is adopted normalization, audio feature selection, and similarity computations based on cosine similarity. It was verified through experiments that the method of normalizing appropriate features by adopting the min–max method and computing similarity using the Euclidean distance was effective.</p>