Integrating ML with Electronic Fiscal Devices for Real-Time Underpricing Detection in Tanzania
DOI:
https://doi.org/10.63158/journalisi.v8i2.1582Keywords:
Electronic Fiscal Devices (EFDs), Machine Learning, Underpricing Fraud, Real-time Detection, Random ForestAbstract
This study aims to develop a machine learning-based tool integrated into Electronic Fiscal Devices (EFDs) to detect underpricing fraud in real time in Tanzania. The motivation for this research arises from the limitations of existing EFD systems, which rely on manual and post-audit mechanisms that are ineffective in identifying fraudulent pricing during transactions. A mixed-methods approach was employed, combining qualitative insights from tax officers with quantitative data collected from traders and buyers. A dataset of 5,000 mobile phone sales transactions collected from Arusha, Dar es Salaam, and Iringa in Tanzania, was pre-processed and used to train and evaluate multiple machine learning models, including Logistic Regression, Support Vector Machine, XGBoost, and Random Forest, using 5-fold cross-validation. The experimental results show that the Random Forest model outperformed other models, achieving an accuracy of 99.6% along with strong precision, recall, and F1-score values. To demonstrate practical applicability, the trained model was further integrated into a prototype EFD environment, where it enabled near real-time fraud detection and generated automated alerts for traders and tax authorities, with geolocation features supporting targeted enforcement. However, the dataset is limited to mobile phone transactions within selected regions of Tanzania, which may affect the generalizability of the findings. The novelty of this study lies in integrating machine learning–based price validation into EFD systems to support proactive detection of underpricing fraud at the point of transaction, thereby enhancing tax compliance and revenue protection.
Downloads
References
[1] E. W. Lubua, “Implication of using electronic fiscal devices on audit effectiveness among small business owners of Arusha–Tanzania,” Pan-African J. Bus. Manag. 7, pp. 41–57, 2023.
[2] J. Longo and N. M. Kenya, “Alignment of Expectations in Electronic Fiscal Devices Adoption: Perspectives of Enforcers and Traders in Tanzania,” sub Sahar. J. Soc. Sci. Humanit., vol. 1, no. 1, pp. 1–10, 2025.
[3] J. B. Ndibalema, N. Mayala, and L. Komba, “Influence of Individual Factors on the Usage of Electronic Fiscal Devices Among Smallholder Taxpayers in Moshi Municipality,” Indian J. Econ. Financ., vol. 5, no. 1, pp. 18–26, 2025.
[4] A. Kalongola, “Impact of Electronic Fiscal Devices.” Institute of Accountancy Arusha (IAA), 2023.
[5] A. B. Bañes, “Tax Management System for Local Government Unit with SMS Notification,” 2023.
[6] E. Njogela, J. Ally, B. Lufyagila, and F. Ruambo, “Mobile Application for Enhancing Revenue Collections in Local Government Authorities. A Case of Tanzania,” East African J. Inf. Technol., vol. 5, no. 1, pp. 164–179, 2022.
[7] P. E. Shao and M. Dida, “The Implementation of an Enhanced EFD System with an Embedded Tax Evasion Detection Features: A Case of Tanzania,” 2020.
[8] B. F. Murorunkwere, J. F. Ihirwe, I. Kayijuka, J. Nzabanita, and D. Haughton, “Comparison of tree-based machine learning algorithms to predict reporting behavior of electronic billing machines,” Information, vol. 14, no. 3, p. 140, 2023.
[9] N. Nuryani, A. B. Mutiara, I. M. Wiryana, D. Purnamasari, and S. N. W. Putra, “Artificial intelligence model for detecting tax evasion involving complex network schemes,” Aptisi Trans. Technopreneursh., vol. 6, no. 3, pp. 339–356, 2024.
[10] S. A. El-Manaseer, J. H. Al-Kayid, A. M. Al Khawatreh, and M. Shamim, “The Impact of Digital Transformation on Combating Tax Evasion (Electronic Billing System as a Model),” in Artificial Intelligence (AI) and Finance, Springer, 2023, pp. 679–690.
[11] S. Shaikh, “Balancing Innovation and Oversight: AI in the US Treasury and IRS: A Survey,” arXiv Prepr. arXiv2509.16294, 2025.
[12] H. E. Nguvava and S. K. Kadenge, “Gross Domestic Product (GDP) determinant of Direct and Indirect Tax Revenue Collection in Tanzania,” Int. J. Econ. Bus. Manag. Res., vol. 08, no. 12, pp. 80–90, 2024, doi: 10.51505/ijebmr.2024.81206.
[13] Nbs, “Tax Statistics Report 2020 / 21 Tanzania Mainland National Bureau of Statistics,” 2024.
[14] H. E. Nguvava and N. N. Athanas, “Performance of Vat System in Tanzania Since Enactment of The Vat Act in 2014,” TIA, 2022.
[15] F. Ramdani, F. Hilmiyah, and V. Indriyani, “The impact of SPSS on research completion,” TOFEDU Futur. Educ. J., vol. 4, no. 2, pp. 419–429, 2025.
[16] A. Demir, S. Demir, and E. K. Sahin, “CatGrass: a feature engineering framework to forecast the seismic response of low-rise RC frames using CatBoost algorithm integrated with grasshopper optimization,” Neural Comput. Appl., vol. 37, no. 22, pp. 18425–18447, 2025.
[17] L. Williams, “Agile software development methodologies and practices,” in Advances in computers, Elsevier, 2010, pp. 1–44.
[18] S. Al-Saqqa, S. Sawalha, and H. AbdelNabi, “Agile software development: Methodologies and trends.,” Int. J. Interact. Mob. Technol., vol. 14, no. 11, 2020.
[19] D. O. Beerbaum, “Applying Agile Methodology to regulatory compliance projects in the financial industry: A case study research,” Available SSRN 3834205, 2021.
[20] A. Raikov, “Decreasing tax evasion by artificial intelligence,” IFAC-PapersOnLine, vol. 54, no. 13, pp. 172–177, 2021.
[21] J. S. Sora, “Determinants of Value Added Tax Performance among Small and Medium Enterprises in Nakuru Central Business District-Kenya,” 2021.
[22] S. R. Gwimile, “Value added tax (VAT) compliance through use of electronic fiscal device (EFD) in Tanzania: a case study of Musoma district in Mara.” Mzumbe University, 2013.
[23] O.-H. Fjeldstad, C. Kagoma, E. Mdee, I. H. Sjursen, and V. Somville, “The customer is king: Evidence on VAT compliance in Tanzania,” World Dev., vol. 128, p. 104841, 2020.
[24] I. Ahmed, G. Jeon, and F. Piccialli, “From artificial intelligence to explainable artificial intelligence in industry 4.0: a survey on what, how, and where,” IEEE Trans. Ind. Informatics, vol. 18, no. 8, pp. 5031–5042, 2022.
[25] J. Martínez-Vázquez, E. Sanz-Arcega, and J. M. T. Martín, “Tax revenue management and reform in the digital era in developing and developed countries,” in Research Handbook on Public Financial Management, Edward Elgar Publishing, 2023, pp. 202–225.
[26] P. Carrillo, D. Donaldson, D. Pomeranz, and M. Singhal, “Ghosting the tax authority: fake firms and tax fraud in Ecuador,” Am. Econ. Rev. Insights, vol. 5, no. 4, pp. 427–444, 2023.
[27] B. Bollinger and S. E. Sexton, “Local excise taxes, sticky prices, and spillovers: evidence from Berkeley’s soda tax,” Quant. Mark. Econ., vol. 21, no. 2, pp. 281–331, 2023.
[28] M. Saarijärvi and E.-L. Bratt, “When face-to-face interviews are not possible: tips and tricks for video, telephone, online chat, and email interviews in qualitative research.” Oxford University Press, 2021.
[29] I. Chiaji, C. Kapkiyai, and D. Kirui, “Tax System Automation and Value Added Tax Compliance; The Moderating Role of Obligation Cost,” South Asian J. Soc. Stud. Econ., vol. 21, no. 10, pp. 1–13, 2024.
[30] B. Chengula, “Underpricing Fraud Detection using Artificial Intelligence Technology to reduce Tax evasion in Tanzaniaa.” Mendeley Data, 2025. doi: 10.17632/YPB66KYDVW.
[31] X. Zhao, R. Lovreglio, and D. Nilsson, “Modelling and interpreting pre-evacuation decision-making using machine learning,” Autom. Constr., vol. 113, p. 103140, 2020.
[32] R.-C. Chen, C. Dewi, S.-W. Huang, and R. E. Caraka, “Selecting critical features for data classification based on machine learning methods,” J. Big Data, vol. 7, no. 1, p. 52, 2020.
[33] F. Ghafouri-Kesbi, “Comparing the performance of xgboost, Gradient Boosting and GBLUP models under different genomic prediction scenarios.,” J. Livest. Sci. Technol., vol. 12, no. 1, 2024.
[34] N. Chhabra Roy and S. P, “Proactive cyber fraud response: a comprehensive framework from detection to mitigation in banks,” Digit. Policy, Regul. Gov., vol. 26, no. 6, pp. 678–707, 2024.
[35] M. F. Younis and Z. S. Alwan, “Monitoring the performance of cloud real-time databases: A firebase case study,” in 2023 Al-Sadiq International Conference on Communication and Information Technology (AICCIT), IEEE, 2023, pp. 240–245.
[36] I. H. Yakin, “Implementation of Human Resources Management in Efforts to Improve the Performance of Tax Instructors,” Atestasi J. Ilm. Akunt., vol. 7, no. 1, pp. 287–299, 2024.
[37] K. Bulubaa, O.-H. Fjeldstad, O. M. Nawab, I. H. Sjursen, and V. Somville, “Improving VAT compliance by incentivizing customers: Evidence from Tanzania,” C. Work. Pap., 2025.
[38] D. Cipullo, D. G. Degl’Innocenti, M. Le Moglie, and F. Passerini, “Inverting the chain? VAT collection regimes and tax compliance,” VAT Collect. regimes tax compliance*(June 29, 2024), 2024.
[39] B. Vyas, “Java in Action: AI for Fraud Detection and Prevention,” Int. J. Sci. Res. Comput. Sci. Eng. Inf. Technol., pp. 58–69, 2023.
[40] N. Shafi, F. Atif, A. Atif, and R. Atif, “The Advanced Feature-Driven Smartphone Price Prediction Using Machine Learning,” J. Res. Artif. Intell. Syst. Appl., vol. 1, no. 2, pp. 14–20, 2025.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Information Systems and Informatics
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors Declaration
- The Authors certify that they have read, understood, and agreed to the Journal of Information Systems and Informatics (JournalISI) submission guidelines, policies, and submission declaration. The submission has been prepared using the provided template.
- The Authors certify that all authors have approved the publication of this manuscript and that there is no conflict of interest.
- The Authors confirm that the manuscript is their original work, has not received prior publication, is not under consideration for publication elsewhere, and has not been previously published.
- The Authors confirm that all authors listed on the title page have contributed significantly to the work, have read the manuscript, attest to the validity and legitimacy of the data and its interpretation, and agree to its submission.
- The Authors confirm that the manuscript is not copied from or plagiarized from any other published work.
- The Authors declare that the manuscript will not be submitted for publication in any other journal or magazine until a decision is made by the journal editors.
- If the manuscript is finally accepted for publication, the Authors confirm that they will either proceed with publication immediately or withdraw the manuscript in accordance with the journal’s withdrawal policies.
- The Authors agree that, upon publication of the manuscript in this journal, they transfer copyright or assign exclusive rights to the publisher, including commercial rights
