Background:

State tax revenue programs face increasing fiscal constraints, making the accurate identification of sales tax noncompliance more critical than ever. Traditionally, identifying sales tax fraud has been labor-intensive, requiring teams of experts and yielding false positives due to human error. With the advent of advanced analytics, machine learning, and AI, tax authorities can now automate the detection of noncompliance, increase efficiency, and enhance the accuracy of enforcement actions.

The Tax Gap Problem:

The U.S. Internal Revenue Service (IRS) estimates a national tax gap of $406 billion, with $291 billion attributed to individual income tax. A significant portion of this is linked to sales tax noncompliance, which also leads to underreporting of income tax, particularly among small business owners. Research indicates that small- and medium-sized businesses, especially those with weak internal controls, are more likely to evade taxes.

IRS tax gap studies highlight that misreporting by small corporations, sole proprietors, and partnerships can reach as high as 64%. This is especially true in businesses where the potential for higher profits from under-reporting makes noncompliance appealing. Traditional methods of enforcement, such as audits and on-site visits, are resource-intensive and often limited in scope.

Solution: nForce Platform

nForce provides a solution that leverages AI and big data analytics to revolutionize tax compliance enforcement. The platform offers advanced algorithms that can handle vast amounts of data across systems, ensuring consistency and accuracy in detecting fraud and other tax-related noncompliance.

The platform uses machine learning and clustering algorithms to automate the detection process, which helps reduce errors and streamline investigations. These advanced techniques allow enforcement agencies to interact securely with the data, minimizing the need for human intervention and reducing the cost and complexity of traditional audits. nForce can often resolve noncompliance through simple letter campaigns, which have proven effective in 70% of cases, significantly cutting down on legal and court procedures.

Case Study: Pilot Program Results

Objective: nForce engaged in a pilot project to analyze 36 months of sales tax filings and business registrations for two NAICS codes (mail-order businesses and convenience stores without gas stations). The primary goal was to identify sales tax noncompliance using AI and advanced analytics.

Methodology:

• Leveraged AWS GovCloud technologies like EC2, S3, Athena, and SageMaker to analyze 1.3 million sales tax records.
• Segmented businesses by type and size and applied machine learning algorithms to predict behaviors within these segments.
• Integrated third-party data (e.g., processor debit and credit transaction data) for detailed analysis.

Results:

• nForce identified approximately $42 million in unremitted sales tax across the 36-month period for the two NAICS codes.
• The analysis was completed within 90 days, significantly faster than the years it would have taken the state Department of Revenue (DOR) using manual methods.
• Noncompliance was identified in three key areas: delinquent reporting, underreported cash sales, and improperly claimed exemptions.
• The nForce platform also uncovered significant data integrity issues, such as the misclassification of businesses under incorrect NAICS codes, which hindered traditional analysis. These issues were remediated using the platform’s large-scale analytics capabilities.

Conclusion:

The nForce platform demonstrated its ability to efficiently detect sales tax noncompliance, saving time and resources for the state DOR. By leveraging AI and big data analytics, the platform not only identified millions of dollars in uncollected revenue but also addressed data integrity issues that traditional systems would have struggled to resolve. With minimal additional resources required, nForce offers state tax authorities a powerful tool to enhance voluntary compliance and improve enforcement operations. This case study highlights the potential of advanced analytics to combat the growing tax gap and optimize revenue collection for essential state services.