Construction of Time Series Prediction Models for Event Influence and Revenue Growth in Sports Industry

This paper builds up the time series analysis model ARIMA, and proposes the measurement and forecasting method of economic revenue growth in sports industry. In order to study the relationship between the influence of events and revenue growth in the sports industry, the VAR model is used as the framework, and an improved time series forecasting model SVAR is proposed. The SVAR model is used to preprocess the influence of events (TYC) and revenue growth (GDP), and complete the smoothness, cointegration, and vector error tests for the variables TYC and GDP. The relationship between TYC and GDP is analyzed in depth, and in the impulse response analysis, the mutual influence between TYC and GDP shows a positive response in the first shock, maintains a more stable positive influence in the long-term shock, and the influence decreases slowly over time. The unidirectional causality between tournament influence and earnings growth is derived by Granger causality test and corroborated in the variance decomposition, which shows that tournament influence and earnings growth have the highest degree of contribution to themselves, but the contribution to each other is relatively low.