ANALYZING MUSIC STREAMING TRENDS WITH SPOTIFY DATA BY MACHINE LEARNING

Abstract

Understanding music streaming trends is essential for identifying user preferences, refining recommendation systems, and guiding strategic decisions in the music industry. This study utilizes Spotify data and applies machine learning models—including Regression, Decision Trees, and Random Forest—to forecast streaming trends and uncover the factors driving song popularity. Key variables such as genre, artist, release year, and user engagement metrics are analyzed to determine their impact on a song’s success. Regression models reveal linear relationships, while Decision Tree and Random Forest models capture complex interactions for improved predictive accuracy. The dataset undergoes thorough preprocessing to eliminate inconsistencies and enhance model performance. Visualizations are used to interpret listener behavior, streaming patterns, and music attributes associated with popular tracks. By incorporating machine learning, this study boosts the effectiveness of trend prediction and personalized recommendations, offering actionable insights for music platforms, artists, and marketers to drive user engagement and satisfaction.