Predicting Ethiopian Gross Domestic Product Using Machine Learning Model - A Data-Driven Regression Approach

Aug 3, 2026

Upload by Riley

Gross Domestic Product (GDP) serves as a comprehensive measure of a country’s total economic activity over a time period, reflecting the monetary value of goods and services produced within national borders. This study forecasts Ethiopia’s GDP with machine learning regression models, including linear, Lasso, ridge, decision tree, random forest, gradient boosting, support vector regression, and neural network regression. Using a National Bank of Ethiopia dataset, the work preprocesses variables and applies 5-fold cross-validation on an 80/20 train-test split. Ridge regression yields the strongest results, with the highest R-squared and lowest error metrics, indicating a high explanatory fit of 99.5% and accurate GDP prediction on the test set.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages26

Reading Time1 h 6 min

AccessFree to download

Abstract

Introduction

GDP as an Economic Indicator

Ethiopia’s Economic Context and Growth Drivers

Role of Machine Learning in Economic Prediction

Limitations of Traditional Statistical Methods

Predicting Ethiopian gross domestic product using machine learning model Elisaye Bekele 1* and Temesgen Zekarias2 1Wolaita Sodo University, Department of Information Technology, Ethiopia, 2Wolaita Sodo University, Department of Economics, Ethiopia *Correspondence author email: [elisaye.bekele@wsu.edu.et](elisaye.bekele@wsu.edu.et), ORCID: [https://orcid.org/0000-0003-1553-33](https://orcid.org/0000-0003-1553-33)[ ](https://orcid.org/0000-0003-1553-33)Received: 18 October 2023; Revised: 08 June 2024; Accepted: 12 June 2024 Abstract The Gross Domestic Product (GDP) is an extensive indicator that reflects all of a country's economic activity over a certain time period. It calculates the total monetary value of all commodities and services produced within the country's borders. We employed a variety of algorithms and models to forecast Ethiopia's GDP using machine learning, including linear regression, Lasso regression, ridge regression, decision tree regression, random forest regression, gradient boosting regression, support vector machine regression, and neural network regression. Three phases comprise our investigation. First, we collect a dataset consisting of several economic statistics from the National Bank of Ethiopia. The gathered dataset is then preprocessed to ensure machine learning models can use it. Ultimately, we partition the dataset, designating 80% of it for model training and the remaining 20% for performance assessment. We employ a 5-fold cross-validation approach and consider evaluation metrics, including R-squared, mean absolute error, root mean square error, and mean squared error, to assess the efficacy of the model. Among all the models, Ridge Regression performs the best, achieving the lowest root mean squared error of 27,231,241,464.13, the highest R-squared value of 0.9950, a mean squared error of 1.06e+20, and a mean absolute error of 21,552,080,423.90 . These results indicate that the model captures 99.5% of the variability in the data. Consequently, using the test dataset, the Ridge Regression model accurately forecasts Ethiopia's GDP. Keywords: Gross Domestic Product; Ethiopia Economy; Machine Learning; Predictive model evaluation; Regression algorithm; Macroeconomic indicators Introduction Gross Domestic Product (GDP) measures the total monetary value of all goods and services produced within a nation's borders over a specific period of time. It serves as a key indicator of economic activity, calculated through the expenditure approach, which combines the spending of households, corporations, and the government (Egbunike and Okerekeoti, 2018) . Gross Domestic Product (GDP) measures a nation's total production of goods and services over a period, providing a comprehensive assessment of its economic state. Comparing GDP over time requires adjusting for inflation. It's typically calculated annually but can be done weekly (Bekaert et al., 2006) . Ethiopia, a developing nation, heavily relies on agriculture, which contributes 43% to its GDP and employs 83% of the population. Despite past growth challenges, the country has seen strong economic growth recently (Abdi et al., 2020) . Ethiopia's GDP in 2022 was $126.78 billion, comprising about 0.06% of the global economy. Despite efforts to bolster the economy, some initiatives have faced challenges, potentially influenced by economic instability elsewhere (Agu et al., 2022) . Ethiopia focuses on industrialization for economic growth, establishing parks and economic zones to attract investments and enhance manufacturing. These efforts have drawn foreign investment and generated jobs, as noted by the World Bank (2019) . Ethiopia modernizes agriculture to boost productivity and alleviate poverty. Initiatives include promoting irrigation, offering farmer support, and investing in research. These efforts have led to higher food production and improved livelihoods (Rohne, 2022) . Ethiopia invests heavily in infrastructure, building roads, rai

FAQs

Which machine learning regression algorithms are used to predict Ethiopia’s GDP?

The study evaluates linear regression, Lasso regression, ridge regression, decision tree regression, random forest regression, gradient boosting regression, support vector machine regression, and neural network regression.

How is the dataset prepared and split for training and evaluation?

A dataset of economic statistics from the National Bank of Ethiopia is collected and preprocessed, then split with 80% for model training and 20% for performance assessment.

What validation method and metrics are used to assess model performance?

The models are evaluated using 5-fold cross-validation and metrics including R-squared, mean absolute error, root mean square error, and mean squared error.

Which model performs best, and how does it affect prediction quality?

Ridge regression performs best, achieving the lowest root mean squared error and the highest R-squared (0.9950), indicating the model captures about 99.5% of variability and accurately forecasts Ethiopia’s GDP on the test dataset.

Aug 3, 2026

Upload by Riley