FDOR Solution for Fuzzy Matching Data (Business Record Linkage)

The Florida Department of Revenue (FDOR) has issued a Request for Information (RFI) seeking services or software that can identify common business and individual entities across different datasets in the absence of common disambiguated identifiers, a process known as "record linkage" or "fuzzy matching". The goal is to provide FDOR with a solution that can definitively demonstrate the ability to find the probability of records being "similar" between disparate datasets, with the express purpose of discovering persons or entities not registered with FDOR that should be, or identifying/providing proof of unreported taxable activities/unpaid tax through these newly discovered record linkages. FDOR is seeking a solution that is easy to use, flexible, scalable, and produces extremely accurate matches, with the ability to process vast amounts of data in short time frames, link multiple data sets, adjust match probabilities for uncertainties, provide transparency, and scale as ongoing jobs or for quick ad hoc runs. Vendor questions are due by noon on February 10, 2023, and vendor responses to the RFI are due by noon on February 27, 2023.

The RFI does not include any set-aside designations or restrictions on the types of organizations that can respond. FDOR is open to exploring various solutions, including cloud-based or third-party hosted options, as long as they comply with IRS Publication 1075 requirements and are FedRAMP certified if hosted outside the FDOR cloud. FDOR prefers a secured REST API to integrate with their existing SSIS packages. The solution should be able to process large volumes of data efficiently and accurately, with the capability to link multiple data sets rather than just a single pair. FDOR is also open to acquiring additional third-party data to supplement their internal data, subject to careful evaluation of the benefits, costs, and impact on data privacy and security. The RFI does not provide any information on award values or budget ranges.