VvictorIkomi/Nigeria-Financial-Crime-AML-Dashboard

Power BI portfolio project for fraud detection, AML risk monitoring, and financial crime investigation using Nigerian transaction data. **Nigeria Financial Crime Intelligence & AML Risk Monitoring Platform** Interactive Power BI dashboards built for fraud detection, AML risk monitoring, and investigation prioritization using the NIBSS Fraud Dataset ________________________________________ **Overview** This project shows how data analytics and visualization can strengthen fraud detection, AML risk monitoring, and investigation prioritization within the Nigerian payments ecosystem. Using the publicly available NIBSS Fraud Dataset, an end to end Financial Crime Intelligence & AML Monitoring Platform was built in Power BI to highlight fraud trends, risk concentration across NIP/POS/USSD channels, customer exposure, and high risk transactional activity. ________________________________________ **Tools Used** • Power BI • Power Query • DAX • Star Schema Data Modelling ________________________________________ **Dataset** • Source: Kaggle – NIBSS Fraud Dataset • Approximately one million transaction records • Country: Nigeria ________________________________________ **Dashboard Screenshots** ## Nigeria Financial Crime Dashboard --- ## Nigeria AML Risk Monitoring Dashboard --- ## Nigeria Crime Investigation Dashboard ________________________________________ **Key Findings** • Fraud activity concentrated in specific channels — Most confirmed cases were linked to a small set of high risk NIBSS channels and merchant categories. • Risk uneven across locations — Certain states showed disproportionately higher exposure compared to the rest of the country. • Only a small share required urgent review — A limited portion of total transactions triggered high risk flags or required immediate analyst attention. • High risk behaviour concentrated among few customers — Suspicious activity was not widespread but clustered around a small group of customers. • Social engineering dominated confirmed fraud — Techniques such as impersonation, phishing, and account takeover accounted for most verified fraud inc …