Predictive analysis of Somalia’s economic indicators using advanced machine learning models

Accurate Gross Domestic Product (GDP) prediction is essential for economic planning and policy formulation. This paper evaluates the performance of three machine learning models—Random Forest Regression (RFR), XGBoost, and Prophet—in predicting Somalia's GDP. Historical economic data, including...

Full description

Saved in:
Bibliographic Details
Main Authors: Bashir Mohamed Osman, Abdillahi Mohamoud Sheikh Muse
Format: Article
Language:English
Published: Taylor & Francis Group 2024-12-01
Series:Cogent Economics & Finance
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/23322039.2024.2426535
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850197377861812224
author Bashir Mohamed Osman
Abdillahi Mohamoud Sheikh Muse
author_facet Bashir Mohamed Osman
Abdillahi Mohamoud Sheikh Muse
author_sort Bashir Mohamed Osman
collection DOAJ
description Accurate Gross Domestic Product (GDP) prediction is essential for economic planning and policy formulation. This paper evaluates the performance of three machine learning models—Random Forest Regression (RFR), XGBoost, and Prophet—in predicting Somalia's GDP. Historical economic data, including GDP per capita, population, inflation rate, and current account balances, were used in training and testing. Among the models, RFR achieved the best accuracy with the lowest MAE (0.6621%), MSE (1.3220%), RMSE (1.1497%), and R-squared of 0.89. The Diebold-Mariano p-value for RFR (0.042) confirmed its higher predictive accuracy. XGBoost performed well but with slightly higher error, yielding an R-squared of 0.85 and p-value of 0.063. In contrast, Prophet had the highest forecast errors, with an R-squared of 0.78 and p-value of 0.015. For enhanced interpretability, SHapley Additive exPlanations (SHAP) were applied to RFR, identifying lagged current account balance, GDP per capita, and lagged population as key predictors, along with total population and government net lending/borrowing. SHAP plots provided insights into these features' contributions to GDP predictions. This study highlights RFR's effectiveness in economic forecasting and emphasizes the importance of current and lagged economic indicators.
format Article
id doaj-art-176f352b3ffa479da8ef5e59d5ac1be4
institution OA Journals
issn 2332-2039
language English
publishDate 2024-12-01
publisher Taylor & Francis Group
record_format Article
series Cogent Economics & Finance
spelling doaj-art-176f352b3ffa479da8ef5e59d5ac1be42025-08-20T02:13:11ZengTaylor & Francis GroupCogent Economics & Finance2332-20392024-12-0112110.1080/23322039.2024.2426535Predictive analysis of Somalia’s economic indicators using advanced machine learning modelsBashir Mohamed Osman0Abdillahi Mohamoud Sheikh Muse1Simad University, Mogadishu, SomaliaDepartment of Management Information System, Cyprus International University, Lefkosa, North CyprusAccurate Gross Domestic Product (GDP) prediction is essential for economic planning and policy formulation. This paper evaluates the performance of three machine learning models—Random Forest Regression (RFR), XGBoost, and Prophet—in predicting Somalia's GDP. Historical economic data, including GDP per capita, population, inflation rate, and current account balances, were used in training and testing. Among the models, RFR achieved the best accuracy with the lowest MAE (0.6621%), MSE (1.3220%), RMSE (1.1497%), and R-squared of 0.89. The Diebold-Mariano p-value for RFR (0.042) confirmed its higher predictive accuracy. XGBoost performed well but with slightly higher error, yielding an R-squared of 0.85 and p-value of 0.063. In contrast, Prophet had the highest forecast errors, with an R-squared of 0.78 and p-value of 0.015. For enhanced interpretability, SHapley Additive exPlanations (SHAP) were applied to RFR, identifying lagged current account balance, GDP per capita, and lagged population as key predictors, along with total population and government net lending/borrowing. SHAP plots provided insights into these features' contributions to GDP predictions. This study highlights RFR's effectiveness in economic forecasting and emphasizes the importance of current and lagged economic indicators.https://www.tandfonline.com/doi/10.1080/23322039.2024.2426535GDP forecastingmachine learningrandom forest regressionSHAPeconomic indicatorsSomalia
spellingShingle Bashir Mohamed Osman
Abdillahi Mohamoud Sheikh Muse
Predictive analysis of Somalia’s economic indicators using advanced machine learning models
Cogent Economics & Finance
GDP forecasting
machine learning
random forest regression
SHAP
economic indicators
Somalia
title Predictive analysis of Somalia’s economic indicators using advanced machine learning models
title_full Predictive analysis of Somalia’s economic indicators using advanced machine learning models
title_fullStr Predictive analysis of Somalia’s economic indicators using advanced machine learning models
title_full_unstemmed Predictive analysis of Somalia’s economic indicators using advanced machine learning models
title_short Predictive analysis of Somalia’s economic indicators using advanced machine learning models
title_sort predictive analysis of somalia s economic indicators using advanced machine learning models
topic GDP forecasting
machine learning
random forest regression
SHAP
economic indicators
Somalia
url https://www.tandfonline.com/doi/10.1080/23322039.2024.2426535
work_keys_str_mv AT bashirmohamedosman predictiveanalysisofsomaliaseconomicindicatorsusingadvancedmachinelearningmodels
AT abdillahimohamoudsheikhmuse predictiveanalysisofsomaliaseconomicindicatorsusingadvancedmachinelearningmodels