The goal of the research focuses on retrieving information from music online website to get the data of the songs with many fields: cover, title, artist, etc. Beside that, we can know about listening music habit of online users based on the statistic chart which shows the listener of the song each day per week. Moreover, this topic has researched time series and seasonal ARIMA (Auto Regressive Integrated Moving Average) model to analyze and predict the number of listeners of the song. Decisions that involve the factor of uncertainty of the future, time series models have been found as effective methods of forecasting.

music information retrieval, ARIMA, song prediction.