Construction of Music Popular Trend Prediction Model Based on Big Data Algorithm

In this paper, a prediction model of music pop trend based on big data algorithm is proposed, and the approximate representation method of time series symbol aggregation based on starting and ending distance is used to predict music pop trend. This method puts forward a new distance measure by combining the symbolic distance and the starting and ending distance, which solves the problem that it is impossible to measure the consistency of symbols in each sequence segment, fully reflects the distance between time series, and effectively improves the effect of distance measurement. The research results show that the average song playing amount is better than the original song playing amount. The F value of the model predicted in this paper is 5064. It is superior to other time series music trend prediction models. Experiments show that this paper uses the approximate representation method of time series symbol aggregation based on the distance from beginning to end to predict the music fashion trend, which solves the problem of predicting the amount of songs played in the research of music fashion trend prediction and the problem of inaccurate prediction caused by the sudden increase of the amount of music data.