Using an Additive Component Model to forecast the number of mergers and acquisitions in China

Abstract

Research is devoted to the topic of modeling and forecasting seasonal fluctuations in MA transactions in China to assess the short-term outlook for the movement of this sector, as well as for future studies of MA market conditions in the PRC. As a forecasting method the authors have chosen a model with an additive component that considers quarterly data on the number of MA deals in the Celestial Empire for the past 15 quarters. The order of building a model with additive component is calculation of seasonal component values, deseasonalization of data, trend calculation and evaluation of forecast accuracy. Additive model allows smoothing seasonality by separating seasonal component from time series and separating it from trend and residual component. This action is performed by subtracting the seasonal component from the original time series. Thus, seasonality is removed from the time series, and only trend and residual component remain. After extraction of the seasonal component, it can be analyzed separately and used to predict future values of the time series. It is also possible to use smoothing methods, such as moving average or exponential smoothing, to smooth the seasonality and get a smoother trend. The authors also built trend models, namely linear, power, polynomial, exponential and logarithmic trend models and chose the polynomial model that provides the highest coefficient of determination. The resulting model has made it possible to forecast the number of transactions by quarter until the end of 2023, in the aftermath of which the possible reasons for the decline in the number of mergers and acquisitions in China are described.

Keywords

• mergers and acquisitions
• m&a
• modeling
• forecasting
• additive component
• trend
• china
• m&a