A Study of the Evolution of Compositional Techniques Applying Time Series Analysis

In the creation of music, compositional techniques play an important role in promoting the future development of music, and strengthening the research on the evolution of compositional techniques is conducive to promoting the prosperity of world music. To this end, the article constructs a time series prediction model based on long and short-term memory network and a differential autoregressive moving average time series model to predict the trend of compositional technique evolution from the perspective of time series prediction, and experimentally verifies and evaluates the prediction effect of these models to achieve the prediction goal. In the experimental test section, the validity and applicability of the two time series prediction models proposed in this paper are verified. The ARIMA model was used to predict the number of music auditions for different compositional techniques from September 1, 2023 to September 30, 2023, and the average relative error was found to be 11.75%.