New Zealand · Wellington · See the New Zealand profile
New Zealand's Inland Revenue uses ML to screen 3+ million tax returns for compliance risk. In H1 2024 this drove a 50% increase in audits opened and NZD 600 million in undeclared tax identified, with NZD 859 million in total compliance revenue.
New Zealand's Inland Revenue (IRD) has used machine-learning models since at least 2022 to screen tax returns and business transactions for compliance risk, prioritising audit resources and flagging cases for review under mandatory human oversight, per IRD's official 'Our use of AI' page.
In the H1 2024 half-year, IRD screened over 3 million returns, flagged 30,000 for review, and opened 3,600 audits (50% more than the prior year), identifying NZD 600 million in undeclared tax and NZD 859 million in total compliance revenue; targeted work also identified NZD 153.5 million in undeclared property/GST income and 227,000 cryptocurrency users with an estimated NZD 2.7 million in unreported income.
Implementation detail (cost, timeline, staffing, conditions for success) is not yet available for this practice.
Where this practice's information was retrieved from, and when.
Ireland
Since 2011, Ireland's Revenue Commissioners have used AI risk scoring (REAP) to target tax-compliance interventions; 290,000 data-analytics-driven interventions in 2023 …
Latvia
Latvia's SRS uses ESCORT ML to score every registered company for fraud risk across tax and labour domains. Fraud detection …
South Africa
South Africa's SARS uses ML models across 1.2 billion annual records to select audits and detect refund fraud. In FY2024/25 …
Italy
Italy's Agenzia delle Entrate deploys VeRa, an AI algorithm cross-referencing declarations with bank data, property records and electronic payments. In …
Open full copilot Grounded in cited practices — always check the sources.