Authors :
Emmanuel Turatsinze; Placide Mukwende; Dr. Fidele Hategekimana; Dr. Pacifique Nizeyimana
Volume/Issue :
Volume 10 - 2025, Issue 7 - July
Google Scholar :
https://tinyurl.com/bdzsaa9m
Scribd :
https://tinyurl.com/mu79pzmj
DOI :
https://doi.org/10.38124/ijisrt/25jul1607
Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.
Note : Google Scholar may take 30 to 40 days to display the article.
Abstract :
Government Fleet Scheme Management in Rwanda has historically relied on manual, paper-based processes,
resulting in inefficiencies, lack of transparency, and forecasting inaccuracies. This work focuses on the development and
evaluation of a web-based platform GFSMIS (Government Fleet Scheme Management Information System) designed to
automate scheme workflows and incorporate predictive analytics using machine learning techniques. A linear regression
model was trained on historical scheme data (2021/2022 to 2023/2024) to predict annual budget from for beneficiaries and
a random forest model was trained on historical data from 2021/2022 to 2025/2026 to predict annual budget for institutions.
GFSMIS integrates user role management, digital signature verification, and real-time data visualization through
dashboards. The linear regression predictive model achieved a Mean Absolute Error (MAE) of 183,217,212 FRW and a
Relative Error of 1.21% for beneficiary schemes, demonstrating high accuracy and the random forest predictive model
achieved a MAE of 428,794,619 FRW with a relative error of 2.13% for institution schemes, demonstrating high accuracy
as well. The system supports fiscal planning, transparency, and automation for national-level decision-making.
Keywords :
MINECOFIN, Government Fleet Scheme, GFSMIS, Beneficiary, FSR, FSM, CBM, MoS and Commissioner of Customs, Budget Forecasting, ML, Linear Regression, Random Forest, Predictive Analytics, Workflow Automation, Rwanda, Public, Digitization, MVC, Java, Weka Library, Spring Core, PostgreSQL.
References :
- López de Prado, Marcos and López de Prado, Marcos, Advances in Financial Machine Learning: Lecture 2/10 (seminar slides) (September 29, 2018). Available at SSRN: https://ssrn.com/abstract=3257415 or http://dx.doi.org/10.2139/ssrn.3257415
- Marcos López de Prado, Frank J. Fabozzi. Crowdsourced Investment Research through Tournaments. Journal of Financial Data Science, Vol. 2, No. 1, 2020, https://jfds.pm-research.com/content/2/1/86
- Ishiki et al., “Measurement and analysis of differential work hardening behavior,” Int. J. Mater. Form., 2023.
- BFI Working Paper, “Machine Learning for Financial Forecasting,” Becker Friedman Institute, 2023.
- Corporate Finance Institute, “Regression Analysis,” [Online]. Available: https://corporatefinanceinstitute.com/ and https://bfi.uchicago.edu/wp-content/uploads/2023/07/BFI_WP_2023-100.pdf
- https://www.minecofin.gov.rw/1/publications/reports
- https://www.researchgate.net/publication/375722976_Machine_Learning_for_Financial_Forecasting
- https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4501707
- https://corporatefinanceinstitute.com/resources/data-science/regression-analysis/
- https://interviewkickstart.com/blogs/articles/financial-forecasting-ml-predictive-analytics#Main
- https://stefanini.com/en/insights/news/machine-learning-models-for-precise-predictive-analytics
- https://www.pyquantnews.com/free-python-resources/machine-learning-for-predictive-financial-analysis
- https://bfi.uchicago.edu/wp-content/uploads/2023/07/BFI_WP_2023-100.pd
Government Fleet Scheme Management in Rwanda has historically relied on manual, paper-based processes,
resulting in inefficiencies, lack of transparency, and forecasting inaccuracies. This work focuses on the development and
evaluation of a web-based platform GFSMIS (Government Fleet Scheme Management Information System) designed to
automate scheme workflows and incorporate predictive analytics using machine learning techniques. A linear regression
model was trained on historical scheme data (2021/2022 to 2023/2024) to predict annual budget from for beneficiaries and
a random forest model was trained on historical data from 2021/2022 to 2025/2026 to predict annual budget for institutions.
GFSMIS integrates user role management, digital signature verification, and real-time data visualization through
dashboards. The linear regression predictive model achieved a Mean Absolute Error (MAE) of 183,217,212 FRW and a
Relative Error of 1.21% for beneficiary schemes, demonstrating high accuracy and the random forest predictive model
achieved a MAE of 428,794,619 FRW with a relative error of 2.13% for institution schemes, demonstrating high accuracy
as well. The system supports fiscal planning, transparency, and automation for national-level decision-making.
Keywords :
MINECOFIN, Government Fleet Scheme, GFSMIS, Beneficiary, FSR, FSM, CBM, MoS and Commissioner of Customs, Budget Forecasting, ML, Linear Regression, Random Forest, Predictive Analytics, Workflow Automation, Rwanda, Public, Digitization, MVC, Java, Weka Library, Spring Core, PostgreSQL.
