Integrating Data Analytics and GIS for Improved Efficiency in Local Tax Audits

Evidence from Samui City Municipality

Abstract

This paper presents a case study of how the State Audit Office of the Kingdom of Thailand (SAO) applied data analytics and geospatial technologies to enhance the effectiveness of a local tax audit in Samui City Municipality. In response to governance challenges following the decentralization of property tax administration, the SAO employed a multidisciplinary methodology combining machine learning, GIS tools, and business intelligence software to assess the completeness, accuracy, and efficiency of land and building tax collection. The audit uncovered widespread data discrepancies, including over 18,000 unregistered properties and significant misclassifications in land use, resulting in under-assessment of tax liabilities. Predictive models identified high-risk taxpayer clusters, while interactive dashboards improved communication of findings. The study highlights the potential of data-driven auditing to uncover systemic weaknesses, recover lost revenue, and promote inter-agency coordination. Key lessons include the need for interoperable data systems, institutional capacity building, and sustained investment in analytics. Despite challenges such as data quality limitations and internal resistance, the audit offers a replicable model for Supreme Audit Institutions (SAIs) seeking to modernize oversight and foster smarter public finance systems in the digital era.