Digitalising Tax Compliance and Elevating Revenue Forecasting in Rwanda: Evidence from Statistical Modelling and Machine Learning

by | Jul 3, 2025 | AMTJ, AMTJ 2025 I1

Digitalising Tax Compliance and Elevating Revenue Forecasting in Rwanda: Evidence from Statistical Modelling and Machine Learning

Author: Clement Uwizeye

ISSN: 2709-8575
Affiliations: Wageningen University & Research (WUR)
Source: African Multidisciplinary Tax Journal, Volume 5, Issue 1 (2025), p. 311–330
https://doi.org/10.47348/AMTJ/V5/i1a15

Abstract

This paper explores the dual role of digitalisation and advanced forecasting models in enhancing tax compliance and revenue prediction in Rwanda. It investigates the impact of electronic billing machine (EBM) adoption on tax performance, the comparative accuracy of traditional econometric models (Bayesian VAR) versus machine learning models (NNAR and Ensemble), and the policy implications of these findings. Using data from 2010 to 2023, the analysis reveals that while EBM usage has expanded significantly, its impact on tax revenue is limited due to enforcement and implementation challenges. Regression results indicate that trade openness, financial development and effective governance positively influence tax revenue, whereas corruption and remittance inf lows pose challenges. Forecasting models indicate a moderately optimistic outlook for tax-to-GDP and trade integration, with NNAR outperforming other models in predictive accuracy. The study concludes with key policy recommendations focused on strengthening digital compliance infrastructure, addressing corruption, supporting financial sector development and leveraging machine learning for more accurate fiscal forecasting. These insights are vital for designing evidence-based tax reforms and achieving sustainable domestic resource mobilisation in Rwanda.

Forecasting Tax Revenue Using Arima and Vector Autoregressiive (VAR) Modelling in Tanzania

by | Jul 3, 2025 | AMTJ, AMTJ 2025 I1

Forecasting Tax Revenue Using Arima and Vector Autoregressiive (VAR) Modelling in Tanzania

Author: Masoud Mohammed Al-biman

ISSN: 2709-8575
Affiliations: Lecturer, Institute of Tax Administration (ITA), Dar-es-Salaam, Tanzania
Source: African Multidisciplinary Tax Journal, Volume 5, Issue 1 (2025), p. 331–352
https://doi.org/10.47348/AMTJ/V5/i1a16

Abstract

This article intends to examine whether times series approaches of ARIMA and VAR are effective in forecasting tax revenue. It also compares the two approaches to evaluate which is the more effective forecasting method. Quarterly data from 1996Q1 to 2016Q4 (21 years or 84 observations) are used to forecast the tax revenue for the period 2017Q1 to 2017Q4. Five common types of taxes are selected due to their significant contributions to Tanzania’s total tax revenue collected by the Tanzania Revenue Authority (TRA). Generally, the results reveal that both time series approaches are effective and demonstrate strong predicting power in short-horizon tax revenue forecasting. However, in most cases that the VAR model outperforms ARIMA modelling, especially based on forecasting criteria. However, we suggest that both methods to be applied by the TRA in forecasting tax revenue as their forecasting errors differ only slightly.

Tax Instruments for the Mining Sector: Profitbased Taxes Versus Production-Based Taxes

Tax Instruments for the Mining Sector: Profitbased Taxes Versus Production-Based Taxes

by | Jul 3, 2024 | AMTJ, AMTJ 2024 I1

Tax Instruments for the Mining Sector: Profitbased Taxes Versus Production-Based Taxes

Author: Kalo Achille Sanou

ISSN: 2709-8575
Affiliations: Université Clermont-Auvergne, CNRS, IRD, CERDI, F-63000 Clermont-Ferrand, France
Source: African Multidisciplinary Tax Journal, Volume 4, Issue 1 (2024), p. 1–17
https://doi.org/10.47348/AMTJ/V4/i1a1

Download PDF

Share

Cite this article

Sanou, K A
Tax Instruments for the Mining Sector: Profitbased Taxes Versus Production-Based Taxes
African Multidisciplinary Tax Journal Volume 4, Issue 1 (2024) p. 1–17
https://doi.org/10.47348/AMTJ/V4/i1a1

Abstract

The sharing of mining rents is a particular challenge for African countries. To explain the determinants of profit-based and production-based taxes, we use a panel of 22 gold-producing countries in Africa between 2000 and 2020 using the ordinary least squares (OLS) method controlled for time and country fixed effects. Our empirical results show that the road distance between the capital of the country and its relevant port is an important indicator in the choice of rent taxation instruments. The road distance between the capital of a country and its relevant port tends to reduce the average effective tax rate (AETR) through the share of profit-based taxes in AETR. Thus, countries that do not have direct access to the sea should favour production-based taxes over profit-based taxes in the taxation of mining rents.

Tax Instruments for the Mining Sector: Profitbased Taxes Versus Production-Based Taxes

Effect of Tax Rates on Industrial Profits on Industrial Production in Sub-Saharan Africa

by | Jul 3, 2024 | AMTJ, AMTJ 2024 I1

Effect of Tax Rates on Industrial Profits on Industrial Production in Sub-Saharan Africa

Authors: Mingnimon Ghislain Gnidehou & Alastaire Sèna Alinsato

ISSN: 2709-8575
Affiliations: Laboratoire d’Economie Publique (LEP), Faculté des Sciences Economiques et de Gestion, Université d’Abomey-Calavi, Benin; Laboratoire d’Economie Publique (LEP), Faculté des Sciences Economiques et de Gestion, Université d’Abomey-Calavi, Benin
Source: African Multidisciplinary Tax Journal, Volume 4, Issue 1 (2024), p. 18–36
https://doi.org/10.47348/AMTJ/V4/i1a2

Download PDF

Share

Cite this article

Gnidehou, M G & Alinsato, A S
Effect of Tax Rates on Industrial Profits on Industrial Production in Sub-Saharan Africa
African Multidisciplinary Tax Journal Volume 4, Issue 1 (2024) p. 18–36 https://doi.org/10.47348/AMTJ/V4/i1a2

Abstract

This paper analyses the effect of the tax rate on industrial profits on industrial production in sub-Saharan Africa. A Seo and Shin dynamic threshold panel model was specified and estimated for this purpose. Using data from the World Bank (WDI) over the period 2005–2021, the results from the estimation of the dynamic threshold model show that there is a threshold from which the effect of the tax rate on profits of industries becomes negative on industrial value added. This is a threshold of 20,47% of the tax rate on industrial profits. Beyond this threshold, the effect of the rate of this type of tax becomes negative on industrial production in Sub-Saharan Africa, precisely in the 25 countries taken into account in this study. The study therefore recommends the implementation of policies favourable to broadening the tax base and moderate tax rates.

Taxation of E-Commerce Activities and Revenue Potential in Ghana

by | Jul 3, 2024 | AMTJ, AMTJ 2024 I1

Taxation of E-Commerce Activities and Revenue Potential in Ghana

Authors: Ammishaddai Owusu-Amoah, Charles Addae, Alex Moyem Kombat*, Douglas Moffatt-Haizel, Felix Ghartey, Israel Elorm Dzokoto, Delali Aku Sunu, Lydia Obeng-Agyei, Stephen Nabareseh, Michael Gyasi, Byrne Joseph Abeiku Yorke, Docia Obiri Asare, Ali-
Kukubor Kobla Jnr, Abdul-Razak Awafo, Christian Nii Welbeck, Julia Ama Senaya†

ISSN: 2709-8575
Affiliations: * Corresponding author. Assistant Commissioner of Tax Research and Policy, Ghana Revenue Authority, † All the authors are affiliated with the Ghana Revenue Authority
Source: African Multidisciplinary Tax Journal, Volume 4, Issue 1 (2024), p. 37–57
https://doi.org/10.47348/AMTJ/V4/i1a3

Abstract

Electronic commerce (e-commerce) businesses have become a common mode of transaction in Ghana. However, Ghana Revenue Authority (GRA) has struggled to assess and maximise its revenue potential due to technical challenges and the complex nature of the market. The main objective of this research was therefore to identify the entities, goods and services involved in online transactions and estimate the total monetary value and revenue potential of online transactions in Ghana. To achieve this, both qualitative and quantitative research methodologies were adopted. The study found that resident and non-resident entities constitute 19 per cent and 81 per cent, respectively of those entities engaged in e-commerce activities in Ghana. Further, it was found that about 20 per cent of students, 45 per cent of people in formal employment, 30 per cent of the self-employed and five per cent of the unemployed are engaged in e-commerce. In addition, it appears that groceries constitute 47.5 per cent of all goods traded online with the rest of the goods constituting 52.5 per cent. Again, as many as 31 per cent of the e-commerce businesses identified in this study had not registered with GRA. Of those registered with GRA, 45 per cent had not filed their corporate income tax (CIT) or personal income tax (PIT). Thirty-eight per cent had not filed their value added tax (VAT), 28 per cent had not filed or paid their pay-as- you-earn (PAYE) and 72.4 per cent of the businesses did not withhold taxes. The paper recommends creating a database for all e-commerce businesses, including those with resident and non-resident status. The estimated revenue potential for e-commerce transactions by resident persons across all types of tax is over GHȻ 1.39 billion.

Dynamics of Taxation and Economic Governance : What Design for the Uemoa Zone?

by | Jul 3, 2024 | AMTJ, AMTJ 2024 I1

Dynamics of Taxation and Economic Governance : What Design for the UEMOA Zone?

Author: Fidel Saliga

ISSN: 2709-8575
Affiliations: Faculté des Sciences Economiques et de Gestion, Université d’Abomey-Calavi
Source: African Multidisciplinary Tax Journal, Volume 4, Issue 1 (2024), p. 58–77
https://doi.org/10.47348/AMTJ/V4/i1a4

Abstract

Financing development is an imperative for any system of governance. Failure in the resource mobilisation process undermines economic growth. The objective of this paper is to analyse the effect of economic governance on public contributions in UEMOA countries. The econometric estimation carried out using the generalised least squares method over the period from 2009 to 2020 shows that governance has a positive and significant effect on total tax revenue. The governments of these WAEMU countries must put in place more effective mechanisms to accelerate the collection of tax revenues while protecting vulnerable taxpayers.