A Machine Learning Approach to Assessing Tax Cuts and Economic Growth in Ghana

Isaac Ampofi; Daniel Andoh Arhinful; Alex Emmanuel Nti; Ernest Mawutor

doi:doi:10.11648/j.ajam.20261405.20

Research Article |

| Peer-Reviewed

A Machine Learning Approach to Assessing Tax Cuts and Economic Growth in Ghana

Isaac Ampofi^*

, Daniel Andoh Arhinful, Alex Emmanuel Nti, Ernest Mawutor

Published in American Journal of Applied Mathematics (Volume 14, Issue 5)

Received: 26 July 2026 Accepted: 7 August 2026 Published: 23 October 2026

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

This study investigates the impact of tax cuts on Ghana's economic growth using a machine-learning approach applied to thirty-five years of macroeconomic data. The analysis focuses on the corporate income tax (CIT) rate, the personal income tax (PIT) rate, foreign direct investment (FDI), inflation, and the sectoral contributions of oil, gold, and cocoa to gross domestic product (GDP). Three feature-engineering strategies namely original, first-differenced, and ratio-transformed variables were used to train and compare an Extreme Gradient Boosting (XGBoost) regression model. The model trained on ratio-transformed features achieved the strongest predictive performance, with a coefficient of determination (R²) of 0.9737, a mean absolute percentage error (MAPE) of 4.12%, and a mean percentage error (MPE) of 0.0986%, substantially outperforming the models trained on the original and first-differenced features. SHapley Additive exPlanations (SHAP) were then applied to interpret the model's predictions. The SHAP analysis shows that higher CIT and PIT rates are consistently associated with lower GDP growth, while FDI inflows and commodity export revenues (particularly gold and oil) are associated with higher growth. These findings suggest that reducing corporate and personal income tax rates could support economic growth in Ghana, but that the benefits of such cuts are likely to be realized only alongside complementary policies that improve investment efficiency, strengthen tax compliance, and add value to commodity exports.

Published in	American Journal of Applied Mathematics (Volume 14, Issue 5)
DOI	10.11648/j.ajam.20261405.20
Page(s)	364-379
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), 2026. Published by Science Publishing Group

Keywords

Tax Cuts, Corporate Income Tax, Personal Income Tax, XGBoost, Machine Learning, SHAP Analysis, Ghana, Economic Growth

References

[1]	Anon. Ghana Fiscal Policy Review. Ministry of Finance Annual Report. 2021, 12(1), 1-55.
[2]	Gashi, P., Pugh, G., Adnett, N. The Effects of Taxation on Economic Growth: Evidence from Transition Economies. Economic Systems. 2018, 42(3), 418-432.
[3]	Nyantakyi, E., Boateng, K., Osei, R. Taxation, Consumption, and Growth in Emerging Economies. African Journal of Economic Policy. 2023, 30(2), 201-220.
[4]	Resnick, D. Taxation and Development in Sub-Saharan Africa: Trends and Policy Challenges. African Development Review. 2016, 23(2), 250-275.
[5]	Akuoko-Konadu, F., Alagidede, P. The Role of Tax Policy in Ghana's Economic Development: A Critical Review. Ghana Economic Journal. 2024, 8(1), 45-60.
[6]	Awadzie, C., Asare, J., Mensah, K. Global Shocks and Domestic Taxation: Evidence from Ghana during the COVID-19 Era. Ghana Journal of Economic Policy. 2022, 12(3), 77-94.
[7]	Gale, W., Samwick, A. Effects of Tax Cuts on Growth: What Do We Know? National Tax Journal. 2017, 70(4), 733-756.
[8]	Gale, W. Fiscal Policy, Tax Cuts, and Economic Recovery: Lessons from History. Brookings Institution Press. 2020, 18(2), 77-99.
[9]	Brys, B., Perret, S., Thomas, A., O'Reilly, P. Tax Policy Reforms in OECD Countries: Trends and Impacts. OECD Tax Policy Studies. 2016, 25(1), 1-156.
[10]	Liu, L. Personal Income Tax Cuts and Household Consumption: Evidence from China. China Economic Review. 2015, 36(1), 110-122.
[11]	Akosah, N. Tax Cuts and Fiscal Sustainability in Ghana. Institute of Economic Affairs Policy Brief. 2015, 6(2), 14-28.
[12]	Ntim, G., Botchway, A. Tax Compliance and Revenue Mobilization in Ghana: Challenges and Policy Solutions. Ghana Journal of Finance. 2023, 12(1), 77-98.
[13]	Ali, A., Asfaw, M. Tax Cuts and Growth Trade-Offs in Developing Economies. Journal of African Fiscal Studies. 2023, 15(2), 66-82.
[14]	Challoumis, C. Understanding the Cycle of Money: Its Impact on Tax Policy and Economic Growth. SSRN Electronic Journal. 2024, 12(1), 1-25. https://doi.org/10.2139/ssrn.4942928
[15]	Auerbach, A. J. Measuring the Effects of Corporate Tax Cuts. Journal of Economic Perspectives. 2018, 32(4), 97-120.
[16]	Altan, A., Karasu, S. The Effect of Kernel Values in Support Vector Machine to Forecasting Performance of Financial Time Series. The Journal of Cognitive Systems. 2019, 4(1), 17-21. https://doi.org/10.1257/jep.32.4.97
[17]	Kazman, L. The Laffer Curve Revisited: Implications for Modern Tax Policy. Journal of Public Economics. 2014, 120(1), 104-116.
[18]	Lin, B., Jia, Z. Tax Policy and Growth: Testing the Laffer Curve in Developing Countries. Economic Modelling. 2019, 77(1), 113-121.
[19]	Lundberg, S. Optimal Taxation and Economic Stagnation: Revisiting the Laffer Curve. Journal of Fiscal Policy. 2024, 18(2), 55-71.
[20]	O'Connor, J. Tax Rates, Incentives, and Government Revenue: Evidence on the Laffer Hypothesis. Public Finance Review. 2017, 45(3), 456-479.
[21]	Ferede, E., Dahlby, B. The Impact of Tax Cuts on Economic Growth: Evidence from Canadian Provinces. National Tax Journal. 2012, 65(3), 563-594. https://doi.org/10.17310/ntj.2012.3.03
[22]	Lee, Y., Gordon, R. Tax Structure and Economic Growth. Journal of Public Economics. 2005, 89(5-6), 1027-1043. https://doi.org/10.1016/j.jpubeco.2004.07.002
[23]	Dladla, K., Khobai, H. Taxation and Economic Growth in South Africa: An ARDL Approach. Journal of Economic Development in Africa. 2018, 13(1), 45-62.
[24]	Zandi, M. The Impact of Tax Policy on Economic Growth and Stability. Moody's Analytics Research Paper. 2010, 12(1), 1-23.
[25]	Ahmad, S., Ali, M., Khan, S. The Impact of Taxation on Economic Growth Using ARDL Approach: A Case Study of Pakistan. Journal of Finance and Economics Research. 2020, 5(2), 89-95. https://doi.org/10.20547/jfer2005202
[26]	Romer, C. D., Romer, D. H. The Macroeconomic Effects of Tax Changes: Estimates Based on a New Measure of Fiscal Shocks. American Economic Review. 2010, 100(3), 763-801. https://doi.org/10.1257/aer.100.3.763
[27]	Dowrick, S. Taxation and Economic Growth in OECD Countries: 1960-1985. Economic Record. 1992, 68(203), 123-135. https://doi.org/10.1111/j.1475-4932.1992.tb01763.x
[28]	Zellner, A., Ngoie, J. K. Evaluation of the Effects of Reduced Personal and Corporate Tax Rates on the Growth Rates of the U.S. Economy. Econometric Reviews. 2015, 34(1-2), 56-81. https://doi.org/10.1080/07474938.2014.944468
[29]	Stoilova, D. Tax Structure and Economic Growth: Evidence from the European Union. Journal of International Economics and Policy. 2017, 20(3), 34-49. https://doi.org/10.1016/j.cya.2017.04.006
[30]	Chigbu, E. E., Njoku, C. O. Taxation and the Nigerian Economy (1994-2012). Management Studies and Economic Systems. 2015, 2(2), 111-128. https://doi.org/10.12816/0019397
[31]	Ebiringa, O. T., Yadirichukwu, E. Analysis of Tax Formation and Impact on Economic Growth in Nigeria. International Journal of Accounting and Financial Reporting. 2012, 2(2), 367-385. https://doi.org/10.5296/ijafr.v2i2.3013
[32]	Okafor, R. G. Tax Revenue Generation and Nigerian Economic Development. European Journal of Business and Management. 2012, 4(19), 49-56.
[33]	Shala, A. VAT Revenue and Economic Growth: Evidence from Kosovo. Journal of Balkan Economic Studies. 2021, 13(4), 55-71.

Cite This Article

Plain Text BibTeX RIS

APA Style

Ampofi, I., Arhinful, D. A., Nti, A. E., Mawutor, E. (2026). A Machine Learning Approach to Assessing Tax Cuts and Economic Growth in Ghana. American Journal of Applied Mathematics, 14(5), 364-379. https://doi.org/10.11648/j.ajam.20261405.20

Copy | Download

ACS Style

Ampofi, I.; Arhinful, D. A.; Nti, A. E.; Mawutor, E. A Machine Learning Approach to Assessing Tax Cuts and Economic Growth in Ghana. Am. J. Appl. Math. 2026, 14(5), 364-379. doi: 10.11648/j.ajam.20261405.20

Copy | Download

AMA Style

Ampofi I, Arhinful DA, Nti AE, Mawutor E. A Machine Learning Approach to Assessing Tax Cuts and Economic Growth in Ghana. Am J Appl Math. 2026;14(5):364-379. doi: 10.11648/j.ajam.20261405.20

Copy | Download

@article{10.11648/j.ajam.20261405.20,
  author = {Isaac Ampofi and Daniel Andoh Arhinful and Alex Emmanuel Nti and Ernest Mawutor},
  title = {A Machine Learning Approach to Assessing Tax Cuts and Economic Growth in Ghana},
  journal = {American Journal of Applied Mathematics},
  volume = {14},
  number = {5},
  pages = {364-379},
  doi = {10.11648/j.ajam.20261405.20},
  url = {https://doi.org/10.11648/j.ajam.20261405.20},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajam.20261405.20},
  abstract = {This study investigates the impact of tax cuts on Ghana's economic growth using a machine-learning approach applied to thirty-five years of macroeconomic data. The analysis focuses on the corporate income tax (CIT) rate, the personal income tax (PIT) rate, foreign direct investment (FDI), inflation, and the sectoral contributions of oil, gold, and cocoa to gross domestic product (GDP). Three feature-engineering strategies namely original, first-differenced, and ratio-transformed variables were used to train and compare an Extreme Gradient Boosting (XGBoost) regression model. The model trained on ratio-transformed features achieved the strongest predictive performance, with a coefficient of determination (R2) of 0.9737, a mean absolute percentage error (MAPE) of 4.12%, and a mean percentage error (MPE) of 0.0986%, substantially outperforming the models trained on the original and first-differenced features. SHapley Additive exPlanations (SHAP) were then applied to interpret the model's predictions. The SHAP analysis shows that higher CIT and PIT rates are consistently associated with lower GDP growth, while FDI inflows and commodity export revenues (particularly gold and oil) are associated with higher growth. These findings suggest that reducing corporate and personal income tax rates could support economic growth in Ghana, but that the benefits of such cuts are likely to be realized only alongside complementary policies that improve investment efficiency, strengthen tax compliance, and add value to commodity exports.},
 year = {2026}
}

Copy | Download

TY  - JOUR
T1  - A Machine Learning Approach to Assessing Tax Cuts and Economic Growth in Ghana
AU  - Isaac Ampofi
AU  - Daniel Andoh Arhinful
AU  - Alex Emmanuel Nti
AU  - Ernest Mawutor
Y1  - 2026/10/23
PY  - 2026
N1  - https://doi.org/10.11648/j.ajam.20261405.20
DO  - 10.11648/j.ajam.20261405.20
T2  - American Journal of Applied Mathematics
JF  - American Journal of Applied Mathematics
JO  - American Journal of Applied Mathematics
SP  - 364
EP  - 379
PB  - Science Publishing Group
SN  - 2330-006X
UR  - https://doi.org/10.11648/j.ajam.20261405.20
AB  - This study investigates the impact of tax cuts on Ghana's economic growth using a machine-learning approach applied to thirty-five years of macroeconomic data. The analysis focuses on the corporate income tax (CIT) rate, the personal income tax (PIT) rate, foreign direct investment (FDI), inflation, and the sectoral contributions of oil, gold, and cocoa to gross domestic product (GDP). Three feature-engineering strategies namely original, first-differenced, and ratio-transformed variables were used to train and compare an Extreme Gradient Boosting (XGBoost) regression model. The model trained on ratio-transformed features achieved the strongest predictive performance, with a coefficient of determination (R2) of 0.9737, a mean absolute percentage error (MAPE) of 4.12%, and a mean percentage error (MPE) of 0.0986%, substantially outperforming the models trained on the original and first-differenced features. SHapley Additive exPlanations (SHAP) were then applied to interpret the model's predictions. The SHAP analysis shows that higher CIT and PIT rates are consistently associated with lower GDP growth, while FDI inflows and commodity export revenues (particularly gold and oil) are associated with higher growth. These findings suggest that reducing corporate and personal income tax rates could support economic growth in Ghana, but that the benefits of such cuts are likely to be realized only alongside complementary policies that improve investment efficiency, strengthen tax compliance, and add value to commodity exports.
VL  - 14
IS  - 5
ER  -

Copy | Download

Author Information

Isaac Ampofi

Department of Mathematical Sciences, University of Mines and Technology, Tarkwa, Ghana

Contact Email

http://orcid.org/0009-0007-3269-6507
Daniel Andoh Arhinful

Department of Mathematical Sciences, University of Mines and Technology, Tarkwa, Ghana
Alex Emmanuel Nti

Department of Mathematical Sciences, University of Mines and Technology, Tarkwa, Ghana
Ernest Mawutor

Department of Mathematical Sciences, University of Mines and Technology, Tarkwa, Ghana

Download PDF

Submit an Article

Sections

Plain Text BibTeX RIS

APA Style

Ampofi, I., Arhinful, D. A., Nti, A. E., Mawutor, E. (2026). A Machine Learning Approach to Assessing Tax Cuts and Economic Growth in Ghana. American Journal of Applied Mathematics, 14(5), 364-379. https://doi.org/10.11648/j.ajam.20261405.20

Copy | Download

ACS Style

Ampofi, I.; Arhinful, D. A.; Nti, A. E.; Mawutor, E. A Machine Learning Approach to Assessing Tax Cuts and Economic Growth in Ghana. Am. J. Appl. Math. 2026, 14(5), 364-379. doi: 10.11648/j.ajam.20261405.20

Copy | Download

AMA Style

Ampofi I, Arhinful DA, Nti AE, Mawutor E. A Machine Learning Approach to Assessing Tax Cuts and Economic Growth in Ghana. Am J Appl Math. 2026;14(5):364-379. doi: 10.11648/j.ajam.20261405.20

Copy | Download

@article{10.11648/j.ajam.20261405.20,
  author = {Isaac Ampofi and Daniel Andoh Arhinful and Alex Emmanuel Nti and Ernest Mawutor},
  title = {A Machine Learning Approach to Assessing Tax Cuts and Economic Growth in Ghana},
  journal = {American Journal of Applied Mathematics},
  volume = {14},
  number = {5},
  pages = {364-379},
  doi = {10.11648/j.ajam.20261405.20},
  url = {https://doi.org/10.11648/j.ajam.20261405.20},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajam.20261405.20},
  abstract = {This study investigates the impact of tax cuts on Ghana's economic growth using a machine-learning approach applied to thirty-five years of macroeconomic data. The analysis focuses on the corporate income tax (CIT) rate, the personal income tax (PIT) rate, foreign direct investment (FDI), inflation, and the sectoral contributions of oil, gold, and cocoa to gross domestic product (GDP). Three feature-engineering strategies namely original, first-differenced, and ratio-transformed variables were used to train and compare an Extreme Gradient Boosting (XGBoost) regression model. The model trained on ratio-transformed features achieved the strongest predictive performance, with a coefficient of determination (R2) of 0.9737, a mean absolute percentage error (MAPE) of 4.12%, and a mean percentage error (MPE) of 0.0986%, substantially outperforming the models trained on the original and first-differenced features. SHapley Additive exPlanations (SHAP) were then applied to interpret the model's predictions. The SHAP analysis shows that higher CIT and PIT rates are consistently associated with lower GDP growth, while FDI inflows and commodity export revenues (particularly gold and oil) are associated with higher growth. These findings suggest that reducing corporate and personal income tax rates could support economic growth in Ghana, but that the benefits of such cuts are likely to be realized only alongside complementary policies that improve investment efficiency, strengthen tax compliance, and add value to commodity exports.},
 year = {2026}
}

Copy | Download

TY  - JOUR
T1  - A Machine Learning Approach to Assessing Tax Cuts and Economic Growth in Ghana
AU  - Isaac Ampofi
AU  - Daniel Andoh Arhinful
AU  - Alex Emmanuel Nti
AU  - Ernest Mawutor
Y1  - 2026/10/23
PY  - 2026
N1  - https://doi.org/10.11648/j.ajam.20261405.20
DO  - 10.11648/j.ajam.20261405.20
T2  - American Journal of Applied Mathematics
JF  - American Journal of Applied Mathematics
JO  - American Journal of Applied Mathematics
SP  - 364
EP  - 379
PB  - Science Publishing Group
SN  - 2330-006X
UR  - https://doi.org/10.11648/j.ajam.20261405.20
AB  - This study investigates the impact of tax cuts on Ghana's economic growth using a machine-learning approach applied to thirty-five years of macroeconomic data. The analysis focuses on the corporate income tax (CIT) rate, the personal income tax (PIT) rate, foreign direct investment (FDI), inflation, and the sectoral contributions of oil, gold, and cocoa to gross domestic product (GDP). Three feature-engineering strategies namely original, first-differenced, and ratio-transformed variables were used to train and compare an Extreme Gradient Boosting (XGBoost) regression model. The model trained on ratio-transformed features achieved the strongest predictive performance, with a coefficient of determination (R2) of 0.9737, a mean absolute percentage error (MAPE) of 4.12%, and a mean percentage error (MPE) of 0.0986%, substantially outperforming the models trained on the original and first-differenced features. SHapley Additive exPlanations (SHAP) were then applied to interpret the model's predictions. The SHAP analysis shows that higher CIT and PIT rates are consistently associated with lower GDP growth, while FDI inflows and commodity export revenues (particularly gold and oil) are associated with higher growth. These findings suggest that reducing corporate and personal income tax rates could support economic growth in Ghana, but that the benefits of such cuts are likely to be realized only alongside complementary policies that improve investment efficiency, strengthen tax compliance, and add value to commodity exports.
VL  - 14
IS  - 5
ER  -

Copy | Download