Today, the music industry has grown tremendously with the emergence of smartphones and streaming services. In the past, the most of revenue was from the album’s sales and concerts. However, these days, streaming services on the web or smartphones have become a huge part of the music industry. Therefore, from an artist’s perspective, it is important to rank their music high on streaming services to earn money. While the music industry is growing, the top 1% of artists have gone from earning 26 percent of revenue to between 56% and 77%. This shows the huge income gap among the artists. Large profit on various artist can help to make a better music business. This paper is written in order to analyze the popular music in Spotify, which is one of the most popular music streaming services in the world. To find the factors that popular music has, this paper analyzes data of 2010~2019 top 50 music on Spotify. The paper also presents the table and graph that clearly illustrate the average of many music factors such as beat per minute and duration to investigate how music should be made to rank high on the Spotify. Moreover, the paper utilizes a machine learning model to predict the popularity of music by analyzing the beat per minute, speecheness, loudness, and duration, etc. The prediction model is expected to be used by many artists or music companies before they release their music.