Forecasting Global Economic Indicators using Convolution Neural Networks

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

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-13
DOI
https://doi.org/10.5281/zenodo.24185997
Primary Topic
Forecasting Techniques and Applications
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Forecasting Global Economic Indicators using Convolution Neural Networks

Satya Srinivas Maddipati, Prof. Mohammed Mustafa
4 links
Zenodo (CERN European Organization for Nuclear Research)
Forecasting Techniques and Applications
article

Forecasting Global Economic Indicators using Convolution Neural Networks

Satya Srinivas Maddipati, Prof. Mohammed Mustafa
article en

Abstract

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

Zenodo (CERN European Organization for Nuclear Research)
Forecasting Techniques and Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon