Public Servant Service Watch System: Leveraging Artificial Intelligence, Machine Learning, and Big Data Analytics to Combat Corruption in Nigeria

Abstract

Public sector fraud continues to undermine governance and development efforts in Nigeria. Despite ongoing anti-corruption campaigns, existing detection mechanisms remain manual, reactive, and insufficiently equipped to flag complex financial irregularities in real time. A critical research gap exists in the integration of automated, data-driven approaches to proactively detect fraud among public officials. This study seeks to bridge that gap by developing and evaluating a machine learning–based system tailored for detecting suspicious financial behaviours using asset declarations and transaction records. The work employed two datasets: a synthetically generated dataset created with Python’s Faker library and publicly available financial transaction data from Kaggle. These were harmonized using unique identifiers, cleaned, and pre-processed to support analysis. Exploratory Data Analysis (EDA) helped uncover patterns relevant to fraud detection, such as transaction spikes and discrepancies between income and declared assets. A Random Forest classifier was chosen for its balance of predictive performance and interpretability. The model was trained and deployed using Microsoft Azure to enable scalable, real-time processing. Results indicate that the Public Servant Service Watch system effectively identifies anomalies such as sudden asset accumulation and undeclared financial interests. The Random Forest model achieved high scores across accuracy, precision, recall, and AUC-ROC metrics. This study demonstrates the feasibility and impact of applying machine learning within a cloud-based infrastructure to improve transparency, accountability, and fraud prevention in the Nigerian public sector.