CYBERJAYA, Nov 3 - The Inland Revenue Board of Malaysia (LHDN) has audited and investigated 408,726 cases throughout this year, resulting in additional tax assessments amounting to about RM7.7 billion.
Its chief executive officer Datuk Abu Tariq Jamaluddin said these compliance and enforcement measures focused on several high-risk areas, including high-net-worth individuals; the tobacco, liquor, and vape sectors; as well as aggressive tax planning activities.
LHDN also paid close attention to transfer pricing issues, e-Invoice data, and information on Malaysian taxpayers’ overseas accounts to ensure compliance with the country's tax laws.
“LHDN has always prioritised voluntary compliance. However, it will take firm action without fear or favour against parties who deliberately evade their tax responsibilities," he said during the opening ceremony of LHDN's 2026 Innovation and Integrity Day celebration today.
Meanwhile, LHDN is intensifying its use of artificial intelligence (AI) technology to improve operational efficiency, strengthen tax compliance, and enhance services for taxpayers.
Among the AI applications developed or currently under development is HAFY-TaxAssist, a chatbot powered by Conversational AI that enables taxpayers to obtain tax-related information and guidance around the clock.
In addition, the Instrument Recognition and Intelligence Model was developed to identify different types of documents or instruments and determine the appropriate stamp duty rates based on the documents' contents.
LHDN also utilises behavioural analytics to analyse the patterns and behaviour of different taxpayer groups, allowing for more targeted monitoring and compliance strategies.
Abu Tariq added that this model helps identify high-risk taxpayer groups by analysing information stored in LHDN's data warehouse.
Another app is the Next-Best Action Predictive Model, which helps LHDN determine the most appropriate tax collection action based on the financial profiles, compliance records, and behavioural patterns of taxpayers with outstanding tax arrears.
Meanwhile, the MyInvois Advanced Analytics Anomaly Detection Model, which harnesses e-Invoice data, has identified more than 7,700 potential tax-risk cases requiring audit and investigation intervention.
He said the AI usage will enable LHDN to move away from conventional compliance approaches towards more proactive, targeted, and data-based methods.
In another development, LHDN has also launched the LHDN Integrity Document as part of its ongoing commitment to strengthen organisational accountability and governance, in line with the LHDNM Anti-Corruption Strategy 2026-2028.
Abu Tariq said the document will serve as the main reference for matters relating to integrity and must be translated into action, with no room for abuse of power, conflicts of interest, or any form of misconduct.