Supervision of Public Funds

Preventing Double Financing / Case

An innovative digital prototype aimed at preventing double financing in public sector projects for the Ministry of Finance of the Republic of Lithuania was developed.

The project targets the issue of funding misuse, where multiple IT systems manage various sources of financing, creating a risk that the same expenses might be funded more than once. 

Objectives

The goal of this client was to create a digital system that automates daily checks across different funding sources to prevent double financing in national projects. The system analyzes project data such as organization codes, activity names, and account numbers from multiple state IT systems. To ensure financial accountability, the prototype  can generate a list of potential double-financing cases and notify administrators via email.

Core system functionalities

The system performs automated daily checks by synchronizing data across the specified external systems, identifying coincidences in legal entity codes, project activities, and account numbers that might signal double financing. A list of potential cases is presented through a user-friendly interface that allows administrators to mark cases as resolved, enter notes, and create detailed reports.

When potential double financing cases are detected, the system automatically notifies the administrators. Email notifications include a summary of the overlaps found, allowing administrators to review and address the issues efficiently. 

The system employs Microsoft Entra ID for secure authentication and Role-Based Access Control to ensure only authorized personnel can access sensitive financial data. All data transfers are encrypted using AES-256 standards, ensuring compliance with GDPR and other relevant data protection regulations.

Technical implementation

The prototype system was built using a microservice architecture, thus ensuring flexibility and scalability for future development. The modular system will allow for easy updates and the potential integration of machine learning to improve data analysis accuracy. It can already support up to 50 concurrent users and ensure a system uptime of at least 96%. The back-end will is developed using Python Flask or Django, integrated with SQL Server for robust data management, and the front-end is built with Next.js and React for an intuitive user experience.

Future prospects

The developed system has the potential for further expansion, particularly by incorporating machine learning and large language models  to improve the accuracy of double-financing detection. This will enable the system to analyze more complex data overlaps, providing deeper insights and reducing false positives. 

Client

Ministry of Finance of the Republic of Lithuania

See the website

Previous
Previous

AI-Powered UAV Systems

Next
Next

Safe & More Efficient Public Transport