AI-Driven Tax Intelligence and Autonomous Compliance Framework for Enterprise Financial Systems

Read full text Summarise with VIRAT
Authors: Jayarami Reddy Pullareddy
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This paper introduces an AI-driven framework for tax intelligence and autonomous compliance in enterprise financial systems. It addresses the limitations of traditional taxation processes, which are often manual, rule-based, and reactive, by leveraging artificial intelligence (AI), machine learning (ML), and enterprise resource planning (ERP) platforms to enable real-time tax validation, anomaly detection, and continuous compliance monitoring. The proposed framework presents a multi-layered architecture consisting of data ingestion, AI-based classification and validation, rule-driven tax engines, compliance automation, and analytics layers. By integrating these components within enterprise environments such as SAP S/4HANA, the model ensures scalability, interoperability, and adherence to evolving regulatory requirements across multiple jurisdictions. The system enhances tax accuracy, reduces manual intervention, and improves audit readiness by enabling automated reconciliation and intelligent decision-making. Additionally, the framework supports predictive compliance by identifying potential discrepancies and risks before they impact financial reporting. This research contributes to the advancement of intelligent finance systems by providing a practical, implementation-ready approach to autonomous taxation and regulatory governance. The findings demonstrate how organizations can transition from periodic, reactive compliance models to continuous, proactive, and AI-driven financial operations.

Fields of Study & Subjects

Robotic Process Automation Applications ERP Systems Implementation and Impact Taxation and Compliance Studies

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
26 March 2026
Language
EN
Document type
Preprint