Forecasting Global Economic Indicators using Convolution Neural Networks
Year: 2026
Type: article
Abstract: . This research presents an effective forecasting approach for global economic indicators, combining Pearson Correlation-based feature selection with Convolutional Neural Networks (CNNs) for time series modelling. The dataset, comprising macroeconomic indicators from over 200 countries between 2010 and 2025, underwent thorough preprocessing to address missing values, outliers, and normalization. Pearson Correlation was employed to identify key features influencing target variables such as GDP growth and inflation, thereby optimizing model input. The CNN architecture, adapted for structured time series, captured temporal patterns and inter-feature relationships using multiple 1D convolutional and dense layers. The model was trained using historical data and evaluated with metrics such as Mean Squared Error (MSE) and Root Mean Squared Error (RMSE). Experimental results demonstrated the superior performance of the CNN-based model, achieving an MSE of 4.67, outperforming traditional models like Decision Trees (9.18), Random Forests (8.63), and Support Vector Machines (8.84). The proposed methodology offers a robust framework for accurate forecasting of key economic indicators, supporting informed policy and economic planning. Keywords: Convolution Neural Networks, Global Economic Indicators
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W7225995472
