Research on the Factors Influencing Business Growth Based on ANN-MLP Algorithm Title Case Taking China Maotai Group as an example

Abstract

The growth of enterprises is the key to the national economy and even the annual economic recovery. Therefore, it is of great theoretical significance and practical value to construct a scientific and effective enterprise growth evaluation model. Multi-layer perceptron (MLP), as a typical representative of artificial neural network (ANN), has the performance of rapid computation and high fault tolerance. In this paper, we take the enterprise data and social data of Maotai Group from 2001 to 2020 as samples, combine enterprise growth theory and, through the literature research method, initially select seven indicators to evaluate enterprise growth and twenty-seven indicators as factors affecting enterprise growth. Then, Kendall correlation coefficient was used to reduce the dimensions of indicators, and the index system of enterprise growth and influencing factors were obtained. Finally, the MLP algorithm was used and optimized to optimize the robustness of the model. The results show that the final model is highly accurate, with MSE of 0.033 and R2 of 0.942, and return on assets and GDP have the greatest influence on firm growth. In other words, the profitability of an enterprise and the country's overall economic prosperity can largely influence the growth of an enterprise, and the stronger the profitability of an enterprise, the stronger its growth ability will be in the era of continuous national economic development. The model has a certain reference value for enterprises to formulate development strategies and the government to formulate macro policies to promote economic growth.