AP Unveils AI/ML-Based GST Administration Model at 6th NCM

AP Tax Department Showcases AI & ML Innovations in GST Administration

In the 6th National Co-ordination Meeting (NCM) conducted at Vigyan Bhawan in New Delhi, the commercial taxes department of Andhra Pradesh presented its Artificial Intelligence (AI) and Machine Learning (ML) driven GST administration model.

The Revenue Secretary, Government of India, chaired the meeting where senior officials from the GST Council Secretariat, the Central Board of Indirect Taxes and Customs (CBIC), and Commercial Tax Commissioners from across the country were present.

Chief Commissioner of State Tax Babu presented the title Use of AI/ML and Automation in GST Tax Administration From Case Selection to Litigation,” and said that how the state has used technology to improve tax compliance and operational efficiency during a dedicated agenda session.

Babu A mentioned that the department had made an integrated AI framework which includes case selection, return scrutiny, GST audits, inspections and litigation management.

The system utlises four data sources, 19 automated analytical reports and a 35-parameter risk matrix to screen cases and route high-value matters for additional scrutiny. He outlined the Legal-AI Officer Assistant, trained on the complete GST statutory corpus and about 22,000 judicial rulings from courts and tribunals.

The engine has been deployed across three litigation forums (the First Appellate Authority, GSTAT, and the HC via the Online Legal Case Management System). It has supported more than 13700 cases by drafting instructions and para-wise remarks, while ensuring human oversight through mandatory officer review and digital signatures.

Babu A outlined the difference between AI-assisted results and traditional manual procedures. Within 6 months of inception, AI-driven return scrutiny furnished revenue detection of Rs 743.43 crore, compared to Rs 365.75 crore recorded in a legacy period.

In manual processes, average detection per case has surged to 27.63 lakh from 3.08 lakh. Automated systems comply with statutory workflows, ensuring traceability through BO Case ID, ARN, and DIN generation, Babu A cited. The Revenue Secretary admired the AP’s framework as a national model for AI-led tax administration, urging delegations from seven states, including Tamil Nadu, Bihar, Rajasthan, Chhattisgarh, Kerala, Assam, and Meghalaya, to visit AP to study the architecture.

Babu A mentioned that plans are in process to expand AI risk-scoring to provisional refunds (RFD-04/RFD-06 processing), arrears recovery, and advance rulings. Suggestions have been furnished by the Chief Commissioner to the Union Government and GSTN, requesting direct GSTN API integration, cross-border taxpayer visibility, and sustained peak-period API access while offering cooperation to share AP’s technological framework with other states.