AI-Driven Data Provenance: Tracking and Verifying Data Lineage

The paper looks into AI-driven data provenance systems for their feasibility in tracing and verification of lineage for healthcare and financial transaction domains. We will use sample data points from Electronic Health Records and transaction data to understand the trade-offs between real-time processing speed and tracking accuracy in the former domain and between detection accuracy and false positives in the latter domain. MATLAB and Python were utilized to analyze the data and model the system. MATLAB was used to create the simulation environment for signal processing tasks, whereas Python, along with libraries such as NumPy and Pandas, facilitated data manipulation, statistical analysis, and generation of visual results. The study comprises impedance and multi-line graphs, which describe the relationships between processing speed, accuracy, and false positives in the systems being investigated. The tables show that processing speed improves healthcare accuracy and finance system detection accuracy and false positives. This means that while AI-driven data provenance systems might improve operational efficiency, they must be adapted to a specific industry to achieve the best balance between performance, accuracy, and reliability. Further development of AI technology using MATLAB and Python should focus on tracking and tracing effective and scalable solution approaches across crucial sectors to validate data lineage.