The automobile manufacturing industry is currently in an important period of transformation and upgrading. Scientific and accurate revenue forecasting model can help automobile manufacturing companies to carry out reasonable business planning, but also can help industry investors and other automobile market participants to understand the business situation. However, revenues of automobile manufacturing companies often show a non-linear dynamic fluctuation trend. To address the aforementioned issues, this research proposes a quarterly revenue prediction model for automobile manufacturing companies based on the machine learning and deep learning algorithm. The overall model is divided into two parts. The first part is based on the random forest and SARIMA algorithm to establish the quarterly sales forecasting model for the automotive industry. The forecasting performance of the model is significantly better than that of the SARIMA model alone. And the performance is better when SARIMA uses dynamic forecasting than when SARIMA uses static forecasting. In the second part, this paper transforms the collected opinion text into data representing the positive degree of opinion sentiment, and builds a model based on the CNN algorithm using the predicted value of automobile industry sales obtained in the first part along with other feature variables. The RMSE and MAE of this prediction model are significantly lower than those of the two benchmark models, so the model proposed in this paper has a better performance on the task of predicting the revenue of automobile manufacturing companies, and the prediction performance of the model is better than that of the model without the introduction of public opinion data.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.