A novel combination machine learning model for regional GDP prediction: evidence from China

Abstract

In recent years, the regional GDP prediction has become an efficient tool to coordinate economic development. This paper aims to study the regional GDP prediction and build a novel machine learning model with taking the entropy method into consideration to predict the future GDP values. This research uses the entropy method to calculate weights of the linear regression model and XGBoost regression model, then build a novel combination model to predict the GDP value of different regions. The model will combine the advantages of trend prediction from linear regression models and high fitting accuracy from XGBoost regression models. In the empirical analysis, the paper used the China's GDP values of different provinces in mainland and built the novel combination model with entropy method, linear regression model and XGBoost regression model. The results reveal that the proposed novel combination model outperforms the tow base models on the mean absolute percentage error evaluation metric.

Nowcasting Madagascar's real GDP using machine learning algorithms

“…XGBoost Regression stands as a cutting-edge machine learning algorithm specifically designed for regression tasks, excelling in predicting GDP [20,43,46,54,67]. It belongs to the gradient boosting family, a framework for sequentially combining weak learners (typically decision trees) to progressively improve prediction accuracy [19,27].…”

“…Machine Learning algorithms have now become a valuable tool in economic modelling, demonstrating remarkable efficacy in the challenging task of nowcasting and forecasting GDP across diverse global contexts. This effectiveness is evident in advanced economies (e.g., Canada [54], China [67,69], Finland [26], Italy [21], Netherlands [42], New Zealand [55,56,60], South Africa [17], Sweden [40], USA [31,45], multiple European countries [23]), emerging markets and developing countries (e.g., Albania [66], Bangladesh [32], Belize and El Savador [5], Brazil [57], Egypt [1], Georgia [46], India [28], Indonesia [62], Lebanon [64], Malaysia [38], Peru [63])). Moreover, Machine learning algorithms are also proved to be very competitive with respect to standard econometric methods.…”