Modelling and Forecasting Unemployment Trends in Kenya Using Advanced Machine Learning Techniques

Reuben Opondo; Davis Bundi; Patrick Weke

doi:doi:10.11648/j.ajtas.20241306.16

Research Article |

| Peer-Reviewed

Modelling and Forecasting Unemployment Trends in Kenya Using Advanced Machine Learning Techniques

Reuben Opondo^*

, Davis Bundi

, Patrick Weke

Published in American Journal of Theoretical and Applied Statistics (Volume 13, Issue 6)

Received: 21 October 2024 Accepted: 18 November 2024 Published: 18 December 2024

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

This study conducts a comprehensive analysis exploring the relationship between key macroeconomic indicators and the unemployment rate, alongside evaluating the predictive accuracy of modern regression models. The correlation analysis examines the association between unemployment rate percentages and five macroeconomic variables: real Gross Domestic Product (GDP) growth, gross public debt as a percentage of GDP, population size, government revenue as a percentage of GDP, and government expenditure as a percentage of GDP. The results highlight significant correlations, particularly the strong positive relationship between unemployment rates and gross public debt (% of GDP) (0.8417), while real GDP growth shows a weak correlation (0.0783), indicating that debt levels may be a more crucial determinant of unemployment variations in this context. Additionally, a comparison of modern regression models, namely Support Vector Regression (SVR), Neural Network Regression, and Bayesian Regression, is conducted based on their performance metrics: Mean Absolute Error (MAE), Root Mean Square Error (RMSE), R-Squared, Akaike Information Criterion (AIC), and Bayesian Information Criterion (BIC). Among the models, Support Vector Regression outperforms the others, with the lowest MAE (0.0823), RMSE (0.0878), and the highest R-Squared value (0.9915), along with notably favourable AIC (-100.2072) and BIC (-69.4268) scores. Neural Network Regression also delivers competitive performance with a slightly higher MAE and RMSE but a similarly strong R-Squared (0.9887). In contrast, Bayesian Regression exhibits weaker predictive power with higher error metrics (MAE = 0.2579, RMSE = 0.3109) and a significantly lower R-Squared (0.8806), AIC (28.0408), and BIC (36.8352). These findings underscore the efficacy of SVR in predictive modelling for macroeconomic datasets, suggesting its suitability for unemployment rate forecasting.

Published in	American Journal of Theoretical and Applied Statistics (Volume 13, Issue 6)
DOI	10.11648/j.ajtas.20241306.16
Page(s)	242-254
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2024. Published by Science Publishing Group

Keywords

Modelling, Machine Learning, Kenya, Unemployment Trends

References

[1]	Barro, R. J., & Gordon, D. B. (1983). Rules, discretion and reputation in a model of monetary policy. Journal of Monetary Economics, 12(1), 101-121. http://dx.doi.org/10.1016/0304-3932(83)90051-X
[2]	Christiano, L. J., Eichenbaum, M., & Evans, C. L. (1999, January 1). Monetary policy shocks: What have we learned and to what end? ScienceDirect; Elsevier. http://dx.doi.org/10.1016/S1574-0048(99)01005-8
[3]	Davis, S. J. (2012). Variations in the wake of labor reallocation. Carnegie-Rochester Conference Series on Public Policy, 27, 335-402. North-Holland.
[4]	Edward, S. (2007). How useful is Okun’s law? Economic Review, 73-103.
[5]	Friedman, M. (2010). Quantity theory of money. MonetaryEconomics, 299-338. https://doi.org/10.1057/978023028085435
[6]	Hu, X. (2017). Support vector machine and its application to regression and classification.
[7]	Karatekin, K., Gocer, I., & Yazar, E. (2015). The relationship between youth unemployment and economic growth in Central and Eastern European countries.
[8]	Meyer, B. D. (1990). Unemployment insurance and unemployment spells. Econometrica, 58(4), 757. https://doi.org/10.2307/2938349
[9]	Mishkin, F. (2004). Why the Federal Reserve should adopt inflation targeting. International Finance, 7(1), 117-127. http://dx.doi.org/10.1111/j.1367-0271.2004.00132.x
[10]	Moses, V. (2019). Does Okun’s law on cyclical unemployment apply in Kenya? International Journal of Current Research, 1765-1770. http://dx.doi.org/10.2139/ssrn.2640519
[11]	Pollin, R., Mwangi wa G˜ith˜inji, & Heintz, J. (2008). An employment-targeted economic program for Kenya. Edward Elgar Publishing.
[12]	Ryan, T. C. I. (2002). Policy timeline and time series data for Kenya.
[13]	Seyfried, W. (2004). Examining the relationship between employment and economic growth in the ten largest states. Southwestern Economic Review, 1-12.
[14]	Sine, W. D. (2010). Institutions and entrepreneurship. RESEARCH in the SOCIOLOGY of WORK, 21, 1-26. http://dx.doi.org/10.1108/S0277-2833(2010)0000021017
[15]	Smola, A. J., & Schölkopf, B. (2004). A tutorial on support vector regression. Statistics and Computing, 14(3), 199-222. https://doi.org/10.1023/b:stco.0000035301.49549.88

Cite This Article

Plain Text BibTeX RIS

APA Style

Opondo, R., Bundi, D., Weke, P. (2024). Modelling and Forecasting Unemployment Trends in Kenya Using Advanced Machine Learning Techniques. American Journal of Theoretical and Applied Statistics, 13(6), 242-254. https://doi.org/10.11648/j.ajtas.20241306.16

Copy | Download

ACS Style

Opondo, R.; Bundi, D.; Weke, P. Modelling and Forecasting Unemployment Trends in Kenya Using Advanced Machine Learning Techniques. Am. J. Theor. Appl. Stat. 2024, 13(6), 242-254. doi: 10.11648/j.ajtas.20241306.16

Copy | Download

AMA Style

Opondo R, Bundi D, Weke P. Modelling and Forecasting Unemployment Trends in Kenya Using Advanced Machine Learning Techniques. Am J Theor Appl Stat. 2024;13(6):242-254. doi: 10.11648/j.ajtas.20241306.16

Copy | Download

@article{10.11648/j.ajtas.20241306.16,
  author = {Reuben Opondo and Davis Bundi and Patrick Weke},
  title = {Modelling and Forecasting Unemployment Trends in Kenya Using Advanced Machine Learning Techniques},
  journal = {American Journal of Theoretical and Applied Statistics},
  volume = {13},
  number = {6},
  pages = {242-254},
  doi = {10.11648/j.ajtas.20241306.16},
  url = {https://doi.org/10.11648/j.ajtas.20241306.16},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajtas.20241306.16},
  abstract = {This study conducts a comprehensive analysis exploring the relationship between key macroeconomic indicators and the unemployment rate, alongside evaluating the predictive accuracy of modern regression models. The correlation analysis examines the association between unemployment rate percentages and five macroeconomic variables: real Gross Domestic Product (GDP) growth, gross public debt as a percentage of GDP, population size, government revenue as a percentage of GDP, and government expenditure as a percentage of GDP. The results highlight significant correlations, particularly the strong positive relationship between unemployment rates and gross public debt (% of GDP) (0.8417), while real GDP growth shows a weak correlation (0.0783), indicating that debt levels may be a more crucial determinant of unemployment variations in this context. Additionally, a comparison of modern regression models, namely Support Vector Regression (SVR), Neural Network Regression, and Bayesian Regression, is conducted based on their performance metrics: Mean Absolute Error (MAE), Root Mean Square Error (RMSE), R-Squared, Akaike Information Criterion (AIC), and Bayesian Information Criterion (BIC). Among the models, Support Vector Regression outperforms the others, with the lowest MAE (0.0823), RMSE (0.0878), and the highest R-Squared value (0.9915), along with notably favourable AIC (-100.2072) and BIC (-69.4268) scores. Neural Network Regression also delivers competitive performance with a slightly higher MAE and RMSE but a similarly strong R-Squared (0.9887). In contrast, Bayesian Regression exhibits weaker predictive power with higher error metrics (MAE = 0.2579, RMSE = 0.3109) and a significantly lower R-Squared (0.8806), AIC (28.0408), and BIC (36.8352). These findings underscore the efficacy of SVR in predictive modelling for macroeconomic datasets, suggesting its suitability for unemployment rate forecasting.},
 year = {2024}
}

Copy | Download

TY  - JOUR
T1  - Modelling and Forecasting Unemployment Trends in Kenya Using Advanced Machine Learning Techniques
AU  - Reuben Opondo
AU  - Davis Bundi
AU  - Patrick Weke
Y1  - 2024/12/18
PY  - 2024
N1  - https://doi.org/10.11648/j.ajtas.20241306.16
DO  - 10.11648/j.ajtas.20241306.16
T2  - American Journal of Theoretical and Applied Statistics
JF  - American Journal of Theoretical and Applied Statistics
JO  - American Journal of Theoretical and Applied Statistics
SP  - 242
EP  - 254
PB  - Science Publishing Group
SN  - 2326-9006
UR  - https://doi.org/10.11648/j.ajtas.20241306.16
AB  - This study conducts a comprehensive analysis exploring the relationship between key macroeconomic indicators and the unemployment rate, alongside evaluating the predictive accuracy of modern regression models. The correlation analysis examines the association between unemployment rate percentages and five macroeconomic variables: real Gross Domestic Product (GDP) growth, gross public debt as a percentage of GDP, population size, government revenue as a percentage of GDP, and government expenditure as a percentage of GDP. The results highlight significant correlations, particularly the strong positive relationship between unemployment rates and gross public debt (% of GDP) (0.8417), while real GDP growth shows a weak correlation (0.0783), indicating that debt levels may be a more crucial determinant of unemployment variations in this context. Additionally, a comparison of modern regression models, namely Support Vector Regression (SVR), Neural Network Regression, and Bayesian Regression, is conducted based on their performance metrics: Mean Absolute Error (MAE), Root Mean Square Error (RMSE), R-Squared, Akaike Information Criterion (AIC), and Bayesian Information Criterion (BIC). Among the models, Support Vector Regression outperforms the others, with the lowest MAE (0.0823), RMSE (0.0878), and the highest R-Squared value (0.9915), along with notably favourable AIC (-100.2072) and BIC (-69.4268) scores. Neural Network Regression also delivers competitive performance with a slightly higher MAE and RMSE but a similarly strong R-Squared (0.9887). In contrast, Bayesian Regression exhibits weaker predictive power with higher error metrics (MAE = 0.2579, RMSE = 0.3109) and a significantly lower R-Squared (0.8806), AIC (28.0408), and BIC (36.8352). These findings underscore the efficacy of SVR in predictive modelling for macroeconomic datasets, suggesting its suitability for unemployment rate forecasting.
VL  - 13
IS  - 6
ER  -

Copy | Download

Author Information

Reuben Opondo

Department of Mathematics, University of Nairobi, Nairobi, Kenya

Contact Email

http://orcid.org/0009-0001-4519-342X
Davis Bundi

Department of Mathematics, University of Nairobi, Nairobi, Kenya

Contact Email

http://orcid.org/0000-0003-3290-0444
Patrick Weke

Department of Mathematics, University of Nairobi, Nairobi, Kenya

Contact Email

http://orcid.org/0000-0002-6283-4567

Download PDF

Sections

Plain Text BibTeX RIS

APA Style

Opondo, R., Bundi, D., Weke, P. (2024). Modelling and Forecasting Unemployment Trends in Kenya Using Advanced Machine Learning Techniques. American Journal of Theoretical and Applied Statistics, 13(6), 242-254. https://doi.org/10.11648/j.ajtas.20241306.16

Copy | Download

ACS Style

Opondo, R.; Bundi, D.; Weke, P. Modelling and Forecasting Unemployment Trends in Kenya Using Advanced Machine Learning Techniques. Am. J. Theor. Appl. Stat. 2024, 13(6), 242-254. doi: 10.11648/j.ajtas.20241306.16

Copy | Download

AMA Style

Opondo R, Bundi D, Weke P. Modelling and Forecasting Unemployment Trends in Kenya Using Advanced Machine Learning Techniques. Am J Theor Appl Stat. 2024;13(6):242-254. doi: 10.11648/j.ajtas.20241306.16

Copy | Download

@article{10.11648/j.ajtas.20241306.16,
  author = {Reuben Opondo and Davis Bundi and Patrick Weke},
  title = {Modelling and Forecasting Unemployment Trends in Kenya Using Advanced Machine Learning Techniques},
  journal = {American Journal of Theoretical and Applied Statistics},
  volume = {13},
  number = {6},
  pages = {242-254},
  doi = {10.11648/j.ajtas.20241306.16},
  url = {https://doi.org/10.11648/j.ajtas.20241306.16},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajtas.20241306.16},
  abstract = {This study conducts a comprehensive analysis exploring the relationship between key macroeconomic indicators and the unemployment rate, alongside evaluating the predictive accuracy of modern regression models. The correlation analysis examines the association between unemployment rate percentages and five macroeconomic variables: real Gross Domestic Product (GDP) growth, gross public debt as a percentage of GDP, population size, government revenue as a percentage of GDP, and government expenditure as a percentage of GDP. The results highlight significant correlations, particularly the strong positive relationship between unemployment rates and gross public debt (% of GDP) (0.8417), while real GDP growth shows a weak correlation (0.0783), indicating that debt levels may be a more crucial determinant of unemployment variations in this context. Additionally, a comparison of modern regression models, namely Support Vector Regression (SVR), Neural Network Regression, and Bayesian Regression, is conducted based on their performance metrics: Mean Absolute Error (MAE), Root Mean Square Error (RMSE), R-Squared, Akaike Information Criterion (AIC), and Bayesian Information Criterion (BIC). Among the models, Support Vector Regression outperforms the others, with the lowest MAE (0.0823), RMSE (0.0878), and the highest R-Squared value (0.9915), along with notably favourable AIC (-100.2072) and BIC (-69.4268) scores. Neural Network Regression also delivers competitive performance with a slightly higher MAE and RMSE but a similarly strong R-Squared (0.9887). In contrast, Bayesian Regression exhibits weaker predictive power with higher error metrics (MAE = 0.2579, RMSE = 0.3109) and a significantly lower R-Squared (0.8806), AIC (28.0408), and BIC (36.8352). These findings underscore the efficacy of SVR in predictive modelling for macroeconomic datasets, suggesting its suitability for unemployment rate forecasting.},
 year = {2024}
}

Copy | Download

TY  - JOUR
T1  - Modelling and Forecasting Unemployment Trends in Kenya Using Advanced Machine Learning Techniques
AU  - Reuben Opondo
AU  - Davis Bundi
AU  - Patrick Weke
Y1  - 2024/12/18
PY  - 2024
N1  - https://doi.org/10.11648/j.ajtas.20241306.16
DO  - 10.11648/j.ajtas.20241306.16
T2  - American Journal of Theoretical and Applied Statistics
JF  - American Journal of Theoretical and Applied Statistics
JO  - American Journal of Theoretical and Applied Statistics
SP  - 242
EP  - 254
PB  - Science Publishing Group
SN  - 2326-9006
UR  - https://doi.org/10.11648/j.ajtas.20241306.16
AB  - This study conducts a comprehensive analysis exploring the relationship between key macroeconomic indicators and the unemployment rate, alongside evaluating the predictive accuracy of modern regression models. The correlation analysis examines the association between unemployment rate percentages and five macroeconomic variables: real Gross Domestic Product (GDP) growth, gross public debt as a percentage of GDP, population size, government revenue as a percentage of GDP, and government expenditure as a percentage of GDP. The results highlight significant correlations, particularly the strong positive relationship between unemployment rates and gross public debt (% of GDP) (0.8417), while real GDP growth shows a weak correlation (0.0783), indicating that debt levels may be a more crucial determinant of unemployment variations in this context. Additionally, a comparison of modern regression models, namely Support Vector Regression (SVR), Neural Network Regression, and Bayesian Regression, is conducted based on their performance metrics: Mean Absolute Error (MAE), Root Mean Square Error (RMSE), R-Squared, Akaike Information Criterion (AIC), and Bayesian Information Criterion (BIC). Among the models, Support Vector Regression outperforms the others, with the lowest MAE (0.0823), RMSE (0.0878), and the highest R-Squared value (0.9915), along with notably favourable AIC (-100.2072) and BIC (-69.4268) scores. Neural Network Regression also delivers competitive performance with a slightly higher MAE and RMSE but a similarly strong R-Squared (0.9887). In contrast, Bayesian Regression exhibits weaker predictive power with higher error metrics (MAE = 0.2579, RMSE = 0.3109) and a significantly lower R-Squared (0.8806), AIC (28.0408), and BIC (36.8352). These findings underscore the efficacy of SVR in predictive modelling for macroeconomic datasets, suggesting its suitability for unemployment rate forecasting.
VL  - 13
IS  - 6
ER  -

Copy | Download