An Unsupervised Machine Learning Framework for Fraud and Anomaly Detection in Nigerian Prepaid Electricity Transactions

Oni Damilola; Okon Paul Godwin; Taiwo Ikeoluwa Odunayo; Akinyooye Demilade Emmanuel; Umoh Samuel Asuquo

doi:doi:10.11648/j.stpp.20250902.16

Research Article |

| Peer-Reviewed

An Unsupervised Machine Learning Framework for Fraud and Anomaly Detection in Nigerian Prepaid Electricity Transactions

Oni Damilola^*, Okon Paul Godwin, Taiwo Ikeoluwa Odunayo, Akinyooye Demilade Emmanuel, Umoh Samuel Asuquo

Published in Science, Technology & Public Policy (Volume 9, Issue 2)

Received: 7 October 2025 Accepted: 5 December 2025 Published: 29 December 2025

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

Prepaid electricity metering is widely adopted in Nigeria to improve revenue collection and reduce customer indebtedness. However, irregularities in transaction records continue to challenge operational reliability and financial transparency. This study presents an unsupervised machine learning framework for detecting anomalies in prepaid electricity transactions using nine months of real-world data. The framework integrates three distinct anomaly detection methods: Isolation Forest, DBSCAN, and a reconstruction-based model using either an Autoencoder or Principal Component Analysis (PCA). These models were combined through a rank-based ensemble scoring system and a majority-vote mechanism to enhance detection of robustness. The dataset includes 23 features spanning customer identifiers, tariff details, and transaction attributes such as energy purchased, payments made, arrears, and VAT. Preprocessing steps involved standardizing column formats, handling missing values, and engineering features such as payment ratios and log-transformed monetary values to improve model sensitivity. Each model independently flagged anomalies, and the ensemble strategy consolidated these outputs to identify high-confidence irregular transactions. The framework uncovered several types of anomalies, including transactions with missing payment and unit values but large arrears repayments, extreme pay-per-unit ratios exceeding operational norms, and VAT entries that deviated significantly from the statutory rate. Spatial analysis revealed concentrated anomalies in specific districts and feeders, suggesting localized vulnerabilities in transaction management and enforcement. Although ground-truth fraud labels were unavailable, the detected anomalies represent statistically significant deviations that warrant further investigation. The results demonstrate that unsupervised models can effectively highlight suspicious patterns without relying on labeled data, offering a scalable approach for utilities to monitor prepaid electricity systems. This methodology supports targeted audits, enhances revenue protection, and contributes to improved regulatory compliance. The study underscores the potential of data-driven techniques in addressing fraud and operational inefficiencies in African energy systems. Future work may incorporate labeled datasets, temporal features, and network-level attributes to refine detection capabilities and expand the scope of analysis.

Published in	Science, Technology & Public Policy (Volume 9, Issue 2)
DOI	10.11648/j.stpp.20250902.16
Page(s)	127-134
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), 2025. Published by Science Publishing Group

Keywords

Unsupervised Machine Learning, Anomaly Detection, Fraud Detection, Prepaid Electricity Transactions, Isolation Forest, DBSCAN, Nigeria Energy Sector

References

[1]	D. Oni, E. Arshad, and B. Pham, Cybercrime On Social Media In Nigeria: Trends, Scams, Vulnerabilities and Prevention, vol. 2. 2023. https://doi.org/10.22624/AIMS/CSEAN-SMART2023P17
[2]	“Evolution of Electricity Metering Technologies in Nigeria \| Nigerian Journal of Technological Development.” Accessed: Dec. 04, 2025. Available: https://www.ajol.info/index.php/njtd/article/view/212538
[3]	D. I.-C. Limited, “NIGERIAN ELECTRICITY REGULATORY COMMISSION.” Accessed: Oct. 07, 2025. Available: https://nerc.gov.ng/
[4]	“Energy Theft Detection and Real-Time Monitoring in a Smart Prepaid Metering System,” Traektori226 Nauki, vol. 10, no. 8, pp. 6029–6037, 2024.
[5]	S. O. Abdulsalam, M. O. Arowolo, R. Babatunde, M. Raji, and S. O. H. Sulyman, “Fraud detection in customers’ electricity consumption in Nigeria using machine learning approach,” Technoscience J. Community Dev. Afr., vol. 2, no. 1, pp. 81-91, 2021.
[6]	O. Nwafor, E. Okafor, A. A. Aboushady, C. Nwafor, and C. Zhou, “Explainable Artificial Intelligence for Prediction of Non-Technical Losses in Electricity Distribution Networks,” IEEE Access, vol. 11, pp. 73104-73115, 2023, https://doi.org/10.1109/ACCESS.2023.3295688
[7]	O. Z. Nwafor, “Artificial Intelligence for Management of Non-Technical Losses in Electricity Distribution Networks in Sub-Saharan Africa: A Case Study of Nigeria.”.
[8]	I. R. Aliu, “Energy efficiency in postpaid-prepaid metered homes: analyzing effects of socio-economic, housing, and metering factors in Lagos, Nigeria,” Energy Effic., vol. 13, no. 5, pp. 853-869, Jun. 2020, https://doi.org/10.1007/s12053-020-09850-y
[9]	M. Ahmed, A. Naser Mahmood, and J. Hu, “A survey of network anomaly detection techniques,” J. Netw. Comput. Appl., vol. 60, pp. 19-31, Jan. 2016, https://doi.org/10.1016/j.jnca.2015.11.016
[10]	“[1901.03407] Deep Learning for Anomaly Detection: A Survey.” Accessed: Oct. 07, 2025. Available: https://arxiv.org/abs/1901.03407
[11]	F. Jamil and E. Ahmad, “Policy considerations for limiting electricity theft in the developing countries,” Energy Policy, vol. 129, pp. 452-458, Jun. 2019, https://doi.org/10.1016/j.enpol.2019.02.035
[12]	V. Hodge and J. Austin, “A Survey of Outlier Detection Methodologies,” Artif. Intell. Rev., vol. 22, no. 2, pp. 85-126, Oct. 2004, https://doi.org/10.1023/B:AIRE.0000045502.10941.a9
[13]	A. Jindal, A. Dua, K. Kaur, M. Singh, N. Kumar, and S. Mishra, “Decision Tree and SVM-Based Data Analytics for Theft Detection in Smart Grid,” IEEE Trans. Ind. Inform., vol. 12, no. 3, pp. 1005-1016, Jun. 2016, https://doi.org/10.1109/TII.2016.2543145

Cite This Article

Plain Text BibTeX RIS

APA Style

Damilola, O., Godwin, O. P., Odunayo, T. I., Emmanuel, A. D., Asuquo, U. S. (2025). An Unsupervised Machine Learning Framework for Fraud and Anomaly Detection in Nigerian Prepaid Electricity Transactions. Science, Technology & Public Policy, 9(2), 127-134. https://doi.org/10.11648/j.stpp.20250902.16

Copy | Download

ACS Style

Damilola, O.; Godwin, O. P.; Odunayo, T. I.; Emmanuel, A. D.; Asuquo, U. S. An Unsupervised Machine Learning Framework for Fraud and Anomaly Detection in Nigerian Prepaid Electricity Transactions. Sci. Technol. Public Policy 2025, 9(2), 127-134. doi: 10.11648/j.stpp.20250902.16

Copy | Download

AMA Style

Damilola O, Godwin OP, Odunayo TI, Emmanuel AD, Asuquo US. An Unsupervised Machine Learning Framework for Fraud and Anomaly Detection in Nigerian Prepaid Electricity Transactions. Sci Technol Public Policy. 2025;9(2):127-134. doi: 10.11648/j.stpp.20250902.16

Copy | Download

@article{10.11648/j.stpp.20250902.16,
  author = {Oni Damilola and Okon Paul Godwin and Taiwo Ikeoluwa Odunayo and Akinyooye Demilade Emmanuel and Umoh Samuel Asuquo},
  title = {An Unsupervised Machine Learning Framework for Fraud and Anomaly Detection in Nigerian Prepaid Electricity Transactions},
  journal = {Science, Technology & Public Policy},
  volume = {9},
  number = {2},
  pages = {127-134},
  doi = {10.11648/j.stpp.20250902.16},
  url = {https://doi.org/10.11648/j.stpp.20250902.16},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.stpp.20250902.16},
  abstract = {Prepaid electricity metering is widely adopted in Nigeria to improve revenue collection and reduce customer indebtedness. However, irregularities in transaction records continue to challenge operational reliability and financial transparency. This study presents an unsupervised machine learning framework for detecting anomalies in prepaid electricity transactions using nine months of real-world data. The framework integrates three distinct anomaly detection methods: Isolation Forest, DBSCAN, and a reconstruction-based model using either an Autoencoder or Principal Component Analysis (PCA). These models were combined through a rank-based ensemble scoring system and a majority-vote mechanism to enhance detection of robustness. The dataset includes 23 features spanning customer identifiers, tariff details, and transaction attributes such as energy purchased, payments made, arrears, and VAT. Preprocessing steps involved standardizing column formats, handling missing values, and engineering features such as payment ratios and log-transformed monetary values to improve model sensitivity. Each model independently flagged anomalies, and the ensemble strategy consolidated these outputs to identify high-confidence irregular transactions. The framework uncovered several types of anomalies, including transactions with missing payment and unit values but large arrears repayments, extreme pay-per-unit ratios exceeding operational norms, and VAT entries that deviated significantly from the statutory rate. Spatial analysis revealed concentrated anomalies in specific districts and feeders, suggesting localized vulnerabilities in transaction management and enforcement. Although ground-truth fraud labels were unavailable, the detected anomalies represent statistically significant deviations that warrant further investigation. The results demonstrate that unsupervised models can effectively highlight suspicious patterns without relying on labeled data, offering a scalable approach for utilities to monitor prepaid electricity systems. This methodology supports targeted audits, enhances revenue protection, and contributes to improved regulatory compliance. The study underscores the potential of data-driven techniques in addressing fraud and operational inefficiencies in African energy systems. Future work may incorporate labeled datasets, temporal features, and network-level attributes to refine detection capabilities and expand the scope of analysis.},
 year = {2025}
}

Copy | Download

TY  - JOUR
T1  - An Unsupervised Machine Learning Framework for Fraud and Anomaly Detection in Nigerian Prepaid Electricity Transactions
AU  - Oni Damilola
AU  - Okon Paul Godwin
AU  - Taiwo Ikeoluwa Odunayo
AU  - Akinyooye Demilade Emmanuel
AU  - Umoh Samuel Asuquo
Y1  - 2025/12/29
PY  - 2025
N1  - https://doi.org/10.11648/j.stpp.20250902.16
DO  - 10.11648/j.stpp.20250902.16
T2  - Science, Technology & Public Policy
JF  - Science, Technology & Public Policy
JO  - Science, Technology & Public Policy
SP  - 127
EP  - 134
PB  - Science Publishing Group
SN  - 2640-4621
UR  - https://doi.org/10.11648/j.stpp.20250902.16
AB  - Prepaid electricity metering is widely adopted in Nigeria to improve revenue collection and reduce customer indebtedness. However, irregularities in transaction records continue to challenge operational reliability and financial transparency. This study presents an unsupervised machine learning framework for detecting anomalies in prepaid electricity transactions using nine months of real-world data. The framework integrates three distinct anomaly detection methods: Isolation Forest, DBSCAN, and a reconstruction-based model using either an Autoencoder or Principal Component Analysis (PCA). These models were combined through a rank-based ensemble scoring system and a majority-vote mechanism to enhance detection of robustness. The dataset includes 23 features spanning customer identifiers, tariff details, and transaction attributes such as energy purchased, payments made, arrears, and VAT. Preprocessing steps involved standardizing column formats, handling missing values, and engineering features such as payment ratios and log-transformed monetary values to improve model sensitivity. Each model independently flagged anomalies, and the ensemble strategy consolidated these outputs to identify high-confidence irregular transactions. The framework uncovered several types of anomalies, including transactions with missing payment and unit values but large arrears repayments, extreme pay-per-unit ratios exceeding operational norms, and VAT entries that deviated significantly from the statutory rate. Spatial analysis revealed concentrated anomalies in specific districts and feeders, suggesting localized vulnerabilities in transaction management and enforcement. Although ground-truth fraud labels were unavailable, the detected anomalies represent statistically significant deviations that warrant further investigation. The results demonstrate that unsupervised models can effectively highlight suspicious patterns without relying on labeled data, offering a scalable approach for utilities to monitor prepaid electricity systems. This methodology supports targeted audits, enhances revenue protection, and contributes to improved regulatory compliance. The study underscores the potential of data-driven techniques in addressing fraud and operational inefficiencies in African energy systems. Future work may incorporate labeled datasets, temporal features, and network-level attributes to refine detection capabilities and expand the scope of analysis.
VL  - 9
IS  - 2
ER  -

Copy | Download

Author Information

Oni Damilola

Department of Informatics and Computer Engineering, Vietnam National University- International School, Hanoi, Vietnam

Contact Email
Okon Paul Godwin

Department of Informatics and Computer Engineering, Vietnam National University- International School, Hanoi, Vietnam

Contact Email
Taiwo Ikeoluwa Odunayo

Department of Informatics and Computer Engineering, Vietnam National University- International School, Hanoi, Vietnam
Akinyooye Demilade Emmanuel

Department of Informatics and Computer Engineering, Vietnam National University- International School, Hanoi, Vietnam
Umoh Samuel Asuquo

Department of Informatics and Computer Engineering, Vietnam National University- International School, Hanoi, Vietnam

Download PDF

Submit an Article

Sections

Plain Text BibTeX RIS

APA Style

Damilola, O., Godwin, O. P., Odunayo, T. I., Emmanuel, A. D., Asuquo, U. S. (2025). An Unsupervised Machine Learning Framework for Fraud and Anomaly Detection in Nigerian Prepaid Electricity Transactions. Science, Technology & Public Policy, 9(2), 127-134. https://doi.org/10.11648/j.stpp.20250902.16

Copy | Download

ACS Style

Damilola, O.; Godwin, O. P.; Odunayo, T. I.; Emmanuel, A. D.; Asuquo, U. S. An Unsupervised Machine Learning Framework for Fraud and Anomaly Detection in Nigerian Prepaid Electricity Transactions. Sci. Technol. Public Policy 2025, 9(2), 127-134. doi: 10.11648/j.stpp.20250902.16

Copy | Download

AMA Style

Damilola O, Godwin OP, Odunayo TI, Emmanuel AD, Asuquo US. An Unsupervised Machine Learning Framework for Fraud and Anomaly Detection in Nigerian Prepaid Electricity Transactions. Sci Technol Public Policy. 2025;9(2):127-134. doi: 10.11648/j.stpp.20250902.16

Copy | Download

@article{10.11648/j.stpp.20250902.16,
  author = {Oni Damilola and Okon Paul Godwin and Taiwo Ikeoluwa Odunayo and Akinyooye Demilade Emmanuel and Umoh Samuel Asuquo},
  title = {An Unsupervised Machine Learning Framework for Fraud and Anomaly Detection in Nigerian Prepaid Electricity Transactions},
  journal = {Science, Technology & Public Policy},
  volume = {9},
  number = {2},
  pages = {127-134},
  doi = {10.11648/j.stpp.20250902.16},
  url = {https://doi.org/10.11648/j.stpp.20250902.16},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.stpp.20250902.16},
  abstract = {Prepaid electricity metering is widely adopted in Nigeria to improve revenue collection and reduce customer indebtedness. However, irregularities in transaction records continue to challenge operational reliability and financial transparency. This study presents an unsupervised machine learning framework for detecting anomalies in prepaid electricity transactions using nine months of real-world data. The framework integrates three distinct anomaly detection methods: Isolation Forest, DBSCAN, and a reconstruction-based model using either an Autoencoder or Principal Component Analysis (PCA). These models were combined through a rank-based ensemble scoring system and a majority-vote mechanism to enhance detection of robustness. The dataset includes 23 features spanning customer identifiers, tariff details, and transaction attributes such as energy purchased, payments made, arrears, and VAT. Preprocessing steps involved standardizing column formats, handling missing values, and engineering features such as payment ratios and log-transformed monetary values to improve model sensitivity. Each model independently flagged anomalies, and the ensemble strategy consolidated these outputs to identify high-confidence irregular transactions. The framework uncovered several types of anomalies, including transactions with missing payment and unit values but large arrears repayments, extreme pay-per-unit ratios exceeding operational norms, and VAT entries that deviated significantly from the statutory rate. Spatial analysis revealed concentrated anomalies in specific districts and feeders, suggesting localized vulnerabilities in transaction management and enforcement. Although ground-truth fraud labels were unavailable, the detected anomalies represent statistically significant deviations that warrant further investigation. The results demonstrate that unsupervised models can effectively highlight suspicious patterns without relying on labeled data, offering a scalable approach for utilities to monitor prepaid electricity systems. This methodology supports targeted audits, enhances revenue protection, and contributes to improved regulatory compliance. The study underscores the potential of data-driven techniques in addressing fraud and operational inefficiencies in African energy systems. Future work may incorporate labeled datasets, temporal features, and network-level attributes to refine detection capabilities and expand the scope of analysis.},
 year = {2025}
}

Copy | Download

TY  - JOUR
T1  - An Unsupervised Machine Learning Framework for Fraud and Anomaly Detection in Nigerian Prepaid Electricity Transactions
AU  - Oni Damilola
AU  - Okon Paul Godwin
AU  - Taiwo Ikeoluwa Odunayo
AU  - Akinyooye Demilade Emmanuel
AU  - Umoh Samuel Asuquo
Y1  - 2025/12/29
PY  - 2025
N1  - https://doi.org/10.11648/j.stpp.20250902.16
DO  - 10.11648/j.stpp.20250902.16
T2  - Science, Technology & Public Policy
JF  - Science, Technology & Public Policy
JO  - Science, Technology & Public Policy
SP  - 127
EP  - 134
PB  - Science Publishing Group
SN  - 2640-4621
UR  - https://doi.org/10.11648/j.stpp.20250902.16
AB  - Prepaid electricity metering is widely adopted in Nigeria to improve revenue collection and reduce customer indebtedness. However, irregularities in transaction records continue to challenge operational reliability and financial transparency. This study presents an unsupervised machine learning framework for detecting anomalies in prepaid electricity transactions using nine months of real-world data. The framework integrates three distinct anomaly detection methods: Isolation Forest, DBSCAN, and a reconstruction-based model using either an Autoencoder or Principal Component Analysis (PCA). These models were combined through a rank-based ensemble scoring system and a majority-vote mechanism to enhance detection of robustness. The dataset includes 23 features spanning customer identifiers, tariff details, and transaction attributes such as energy purchased, payments made, arrears, and VAT. Preprocessing steps involved standardizing column formats, handling missing values, and engineering features such as payment ratios and log-transformed monetary values to improve model sensitivity. Each model independently flagged anomalies, and the ensemble strategy consolidated these outputs to identify high-confidence irregular transactions. The framework uncovered several types of anomalies, including transactions with missing payment and unit values but large arrears repayments, extreme pay-per-unit ratios exceeding operational norms, and VAT entries that deviated significantly from the statutory rate. Spatial analysis revealed concentrated anomalies in specific districts and feeders, suggesting localized vulnerabilities in transaction management and enforcement. Although ground-truth fraud labels were unavailable, the detected anomalies represent statistically significant deviations that warrant further investigation. The results demonstrate that unsupervised models can effectively highlight suspicious patterns without relying on labeled data, offering a scalable approach for utilities to monitor prepaid electricity systems. This methodology supports targeted audits, enhances revenue protection, and contributes to improved regulatory compliance. The study underscores the potential of data-driven techniques in addressing fraud and operational inefficiencies in African energy systems. Future work may incorporate labeled datasets, temporal features, and network-level attributes to refine detection capabilities and expand the scope of analysis.
VL  - 9
IS  - 2
ER  -

Copy | Download