Bank Negara Malaysia (BNM) and Payments Network Malaysia Sdn Bhd (PayNet) are developing an artificial intelligence (AI)-based fraud detection system aimed at reducing online scams and fraudulent transactions. The system is targeted for rollout in 2026.

AI And Machine Learning To Predict Fraudulent Transfers

BNM deputy governor Datuk Marzunisham Omar said the system will use machine learning, large language models, and AI to analyse transaction data and detect suspicious activity.

Through predictive analysis, the system will alert users if a bank transfer appears unsafe and prompt a confirmation message such as, “Are you sure you want to make this transfer?” before the transaction is completed.

“This predictive analysis is something we are working on, and I hope we will be able to roll it out sometime next year,” said Marzunisham during a panel session at the launch of the October 2025 World Bank Malaysia Economic Monitor report.

Strengthening Efforts Against Scams And Mule Accounts

Marzunisham said the initiative is part of BNM’s broader strategy to combat mule accounts and enhance consumer protection in the digital financial ecosystem.

The central bank has been working closely with the financial industry to improve fraud prevention frameworks, especially amid the rise in online scam cases across Malaysia.

Encouraging Responsible Innovation In Digital Finance

BNM’s efforts also extend to encouraging innovation through the Digital Asset Innovation Hub, which provides a controlled environment for regulators, financial institutions, and private sector players to test and develop new financial technologies.

“This hub is an important initiative to encourage innovation in a safe environment,” Marzunisham said.

He added that finance remains one of the fastest-growing sectors in digital adoption, particularly in banking, payments, and financial services.

Financial Industry Moving Towards Responsible AI Use

According to Marzunisham, a survey by the Asian Institute of Chartered Bankers (AICB) found that more than 70% of financial institutions in Malaysia are already exploring AI and generative AI applications.

The AICB is also developing an industry-wide framework to guide the responsible use of AI in the financial sector. This framework aims to ensure innovation is balanced with strong governance and risk management standards.

PayNet Exploring FinancialGPT For Fraud Detection

Separately, PayNet is exploring the creation of a federated AI model known as FinancialGPT, designed to enhance fraud detection and data security in Malaysia’s digital payment systems.

PayNet chief of staff Dr Endry Lim Zhen Wan said the model would be trained exclusively on Malaysia’s financial transaction data to ensure data sovereignty and resilience against cyber threats.

“We believe this model would tackle fraud and scams, ensure broader financial inclusion, and address compliance challenges specific to our market, while ensuring sensitive data never leaves the country,” said Dr Lim.

He added that FinancialGPT combines global best practices with local regulatory needs, making it well suited to Malaysia’s financial environment.

Malaysia Facing Growing Online Scam Losses

The need for stronger fraud prevention systems has become more urgent. According to the Home Ministry, Malaysia recorded RM1.12 billion in losses from online fraud in the first half of 2025, following a record RM1.58 billion in reported losses in 2024.

Follow us on our official WhatsApp channel for the latest money tips and updates.

• TAGS:
• AI Fraud
• Bank Negara Malaysia
• BNM
• FinancialGPT
• Fraud
• Payments Network Malaysia Sdn Bhd
• PayNet