Predicting Customs Fraud Using Machine Learning and Mirror Analysis in Togo

Predicting Customs Fraud Using Machine Learning and Mirror Analysis in Togo

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

Predicting Customs Fraud Using Machine Learning and Mirror Analysis in Togo

Authors: Pouwemdéou Tchila, Komlan Kawa Agbanho and Abalo Bouwe

ISSN: 2709-8575
Affiliations: Docteur en sciences économiques, Data scientiste, Chef division analyse risques et suiviévaluation, Office Togolais des Recettes & Chercheur associé au CREAMO (Université de Lomé); Docteur en sciences économiques, Inspecteur des Douanes, Chef section brigade à la Division des Opérations Douanières de Kwadjoviakopé de l’Office Togolais des Recettes; Master en Statistiques & Mathématiques, Data scientiste, Chargé de l’analyse des risques et de la programmation fiscale, Office Togolais des Recettes
Source: African Multidisciplinary Tax Journal, Volume 5, Issue 1 (2025), p. 1–26
https://doi.org/10.47348/AMTJ/V5/i1a1

Download PDF

Share

Cite this article

Tchila P; Agbanho KK; Bouwe A
Predicting Customs Fraud Using Machine Learning and Mirror Analysis in Togo
African Multidisciplinary Tax Journal Volume 5, Issue 1 (2025) p. 1–26
https://doi.org/10.47348/AMTJ/V5/i1a1

 

Abstract

Customs fraud is an inherent phenomenon of customs administrations and is most often responsible for undermining customs revenue collection. In an attempt to combat this phenomenon, customs administrations, particularly in developing countries, often conduct extensive and unstructured audits. This is not conducive to the fluidity of international trade. The objective of this study is to analyse the extent to which the use of machine learning and mirror analysis improves the identification of customs fraud, while preserving the objective of revenue mobilisation. Using data from the Togolese Revenue Authority and COMTRADE, the findings indicate that mirror analysis and machine learning can better enhance customs fraud detection. To this end, the study recommends the use of these tools in fraud detection.

Predicting Customs Fraud Using Machine Learning and Mirror Analysis in Togo

Understanding the Tax Payment Compliance of Companies: Evidence from Eswatini

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

Understanding the Tax Payment Compliance of Companies: Evidence from Eswatini

Authors: Phindile T Masuku, Dr Fabrizio Santoro and Ziyanda T Dlamini

ISSN: 2709-8575
Affiliations: Manager, Research, Strategy and Statistics Division at the Eswatini Revenue Service; Research Fellow, Institute of Development Studies; Economic Analyst, Research, Strategy and Statistics Division at the Eswatini Revenue Service
Source: African Multidisciplinary Tax Journal, Volume 5, Issue 1 (2025), p. 27–50
https://doi.org/10.47348/AMTJ/V5/i1a2

Download PDF

Share

Cite this article

Masuku PT; Dr Santoro F, Dlamini ZT
Understanding the Tax Payment Compliance of Companies: Evidence from Eswatini
African Multidisciplinary Tax Journal Volume 5, Issue 1 (2025) p. 27–50
https://doi.org/10.47348/AMTJ/V5/i1a2

 

Abstract

This paper investigates corporate income tax (CIT) payment compliance among corporations in Eswatini, an underexplored area critical for revenue-constrained low and middle-income countries. Using a unique administrative dataset (2017–2022), we analyse factors driving timely and full tax payments. We combine descriptive analysis with a more robust Heckman selection model to address sample selection bias. Results show that, while 82% of filed returns included payments, only 55% were fully compliant, and 42% were late. Compliance was higher among larger firms and those in urban tertiary sectors, while smaller and rural firms frequently overpaid, potentially due to penalties. Electronic payments exhibited the highest compliance, whereas mobile and cash payments lagged. Regression analysis highlights company size, provisional tax filings and electronic payments as key compliance predictors. This study contributes to the tax compliance literature with actionable insights for revenue authorities, from the simplification of tax processes for smaller firms to the larger implementation of electronic tax payments.

Tax Revenue Mobilisation in Sub-Saharan Africa: the Role of Tax Administration Reforms

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

Tax Revenue Mobilisation in Sub-Saharan Africa: the Role of Tax Administration Reforms

Authors: Franky Brice Afia Kogueda; Etgard Manga Engama; Martin Eloundou Dzana

ISSN: 2709-8575
Affiliations: Groupe de Recherche en Économie et Gestion [GREG], Université de Douala / École Supérieure des Sciences Economiques et Commerciales [ESSEC] de Douala, Douala-Cameroun; Université de Douala / École Supérieure des Sciences Economiques et Commerciales [ESSEC] de Douala, Douala-Cameroun; Université de Douala / École Supérieure des Sciences Economiques et Commerciales [ESSEC] de Douala, Douala-Cameroun, Centre de Recherche, d’Innovation et de Développement Agricoles (CARID), Douala-Cameroun
Source: African Multidisciplinary Tax Journal, Volume 5, Issue 1 (2025), p. 51–76
https://doi.org/10.47348/AMTJ/V5/i1a3

Abstract

This study aims to demonstrate the impact of tax administration reforms on the mobilisation of direct and indirect taxes from non-natural resources. Out of 40 SSA countries. The assessed tax administration reforms are the establishment of a semi-autonomous revenue administration [SARA], a Large Business Collection Unit [LTU] and an Informal Sector Business Unit or strategy [ISU]. To this end, we use a seemingly unrelated regression [SURE] panel method on data from various sources. The results show that SARAs and LTUs positively impact the mobilisation of direct taxes. However, SARAs do not have an independent impact on indirect taxes and must be used alongside ISUs. ISUs have a positive impact on the mobilisation of indirect taxes. Reorganising tax administration in relation to taxpayers has a positive impact on tax revenue.

A Panel Data Analysis of Tax Revenue Productivity after Semi-Autonomous Revenue Authority Reform

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

A Panel Data Analysis of Tax Revenue Productivity after Semi-Autonomous Revenue Authority Reform

Author: Isaac Yamikani Chilima

ISSN: 2709-8575
Affiliations: PhD in Economics, Yokohama National University, 2019. Associate Professor of Economics and Business, Lead Faculty and Chair of Economics, School of Business and Leadership, Colorado Christian University, USA
Source: African Multidisciplinary Tax Journal, Volume 5, Issue 1 (2025), p. 77–106
https://doi.org/10.47348/AMTJ/V5/i1a4

Abstract

Since the 1980s, over 30 developing countries have adopted semi-autonomous revenue authorities (SARAs) to improve tax administration. This study provides new panel-based evidence on their effectiveness, using data from 30 countries between 1980 and 2016. Applying dynamic ordinary least squares (DOLS) and fixed effects (LSFE) models, we compare tax revenue performance before and after SARA implementation. Across six regional and temporal samples, post-reform tax buoyancy consistently exceeded pre-reform levels, with significant gains ranging from 0.134 to 0.373 percentage points. In the broadest sample, buoyancy rose from 0.979 to 1.125 – a 14.9% increase in responsiveness to GDP. The strongest improvements occurred in sub-Saharan Africa, where SARAs typically enjoy greater autonomy. These findings highlight the importance of institutional design. SARAs that are insulated from political interference and granted managerial flexibility tend to perform better. The results have clear policy relevance for governments seeking to strengthen revenue performance through tax administration reform.

Economic Analysis of the Fairness of the Land Tax System in Benin

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

Economic Analysis of the Fairness of the Land Tax System in Benin

Author: Jonas Fassinou

ISSN: 2709-8575
Affiliations: Chaire ‘Organisation Mondiale du Commerce – Commerce International et Développement Inclusif ’ (OMC-CIDI), Université d’Abomey-Calavi (UAC), Bénin. Cabinet d’Etudes, de Recherche, de Management et de la Qualité (CERMAQ Sarl), Bénin
Source: African Multidisciplinary Tax Journal, Volume 5, Issue 1 (2025), p. 107–130
https://doi.org/10.47348/AMTJ/V5/i1a5

Abstract

This study provides an economic assessment of the fairness of property taxes, establishing a link between tax compliance and the performance of property tax collection in Benin. We first examine the distributional tools used to analyse the fairness of tax systems, namely the concentration curves and the Kakwani (K) and Reynolds-Smolensky (RS) synthetic indices. On the one hand, the results showed that in the municipalities covered by the study, namely Cotonou, Abomey-Calavi and Parakou, the tax concentration curves were higher than those of gross rental values. On the other hand, the calculated values of the indices that measure the extent of progressivity are too low, or even negative. These values range from -0.54 to 0.23 for the Kakwani (K) index, and from -0.17 to 0.0006 for the Reynolds-Smolensky (RS) index. Therefore, the property tax system in Benin is not progressive. Therefore, small landowners pay higher taxes than wealthy landowners. To improve the mobilisation of tax resources in Benin, the country’s authorities must adopt new land property valuation approaches to ensure the land taxation system is progressive.

Economic Assessment of the Impact of the Plastics Excise Tax on Plastic Waste Management in Ghana

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

Economic Assessment of the Impact of the Plastics Excise Tax on Plastic Waste Management in Ghana

Author: Alex Moyem Kombat; Anthony Kwasi Sarpong; Julie Essiam; Charles Addae; Kwabena Apau Anto

ISSN: 2709-8575
Affiliations: Corresponding author, Assistant Commissioner for Tax Research and Policy, Ghana Revenue Authority
Source: African Multidisciplinary Tax Journal, Volume 5, Issue 1 (2025), p. 131–150
https://doi.org/10.47348/AMTJ/V5/i1a6

Abstract

Ghana is one of a few African countries that have implemented a plastics excise tax for plastic litter control and prevention, and for revenue purposes. However, the impact of the Ghanaian plastics excise tax on plastic litter has not been assessed. The aim of this study, therefore, is to assess the impact of the plastics excise tax on plastics litter in Ghana using the goal attainment criterion. A qualitative research methodology was adopted: semi-structured interviews were conducted with relevant stakeholders using the purposive sampling technique. Excel was employed along with descriptive statistics. The study showed that the tax has, to some extent, helped to encourage recycling to create a market for plastic waste, which has reduced the plastic litter, but not to zero. The study also showed that the tax has helped to increase public awareness of the tax, but has failed to reduce the production and consumption of plastics as there is an increased demand for and consumption of plastics in Ghana. However, the tax has been successful in promoting international plastic waste technology transfers in Ghana: the number of recycling entities increased from two in 2008 to 30 in 2022, in a drastic reduction in plastic litter. Against this backdrop, the authors make the following recommendations to improve the plastics excise tax policy: (1) Introduction of direct and variable tax rates based on plastic types and weight at the household level to improve the incentive effect; (2) Government should enact legislation to make it mandatory for plastic manufacturers to recycle their plastic trash; (3) Government should provide subsidies for the production of plastic substitutes, such as paper bags, cloth carrying bags, jute bags, leather bags and shopping cane baskets, to make them attractive to consumers and reduce the demand for plastic bags; and (4) Tax rates should be adjusted to account for inflation.