Financial Index Data Prediction Based on Improved GBDT Model

Business income is an important part of business income, especially the financial index. Achieving financial index prediction has great significant for business operations. However, most financial index forecasting processes are time-consuming and error-prone, as they are manually calculated by hundreds of financial analysts to obtain financial indices. In addition, this type of data usually has data noise and multiple data characteristic variables, As a result, typical statistical approaches have a hard time predicting it. Furthermore, the data collection in this article is tiny, making it unsuitable for models like neural networks, which have higher data volume needs. In this paper, we decided to solve this type of problem by using various models such as gradient boosting regression trees to predict the business revenue data of enterprises.The models' prediction is then evaluated using three metrics: mean absolute error (MAE), root mean square error (RMSE), and absolute error value (MAPE).