TLDR: Bank Negara Malaysia (BNM) and Payments Network Malaysia (PayNet) are set to launch an AI-powered fraud detection system in 2026. This initiative, leveraging machine learning and large language models, aims to provide real-time predictive analysis to protect consumers from rising online scams, which caused RM1.12 billion in losses in the first half of 2025.
KUALA LUMPUR – Bank Negara Malaysia (BNM) and Payments Network Malaysia Sdn Bhd (PayNet) are on track to introduce a sophisticated artificial intelligence-based fraud detection system in 2026, marking a significant step in the nation’s fight against financial crime. The announcement was made by BNM deputy governor Datuk Marzunisham Omar during a panel session at the release of the October 2025 World Bank Malaysia Economic Monitor report.
The new system is meticulously designed to utilize cutting-edge machine learning, large language models, and other AI technologies to perform predictive analysis on existing transaction data. This advanced capability will enable financial institutions to identify and flag potentially fraudulent bank transfers in real-time. Datuk Marzunisham Omar elaborated on its functionality, stating, “We could alert the customer whether a bank transfer is safe or potentially fraudulent, and it will be able to ask ‘Are you sure you want to make this transfer?’ before the transaction is confirmed. This predictive analysis is something we are working on, and I hope we will be able to roll it out sometime next year.”
This initiative is a crucial component of BNM’s broader strategy to combat the proliferation of mule accounts and enhance public protection against the escalating threat of online scams. The urgency of this system is underscored by alarming statistics: Malaysia recorded a staggering RM1.58 billion in losses from online scams in 2024, with an additional RM1.12 billion lost in the first half of 2025 alone.
PayNet, a key partner in this endeavor, is actively exploring the development of a federated AI model, tentatively named FinancialGPT. This model is intended to further bolster fraud detection and strengthen security within the digital payments ecosystem. Dr. Endry Lim Zhen Wan, PayNet’s chief of staff, emphasized the strategic importance of this localized approach: “We believe this model would tackle fraud and scams, ensure broader financial inclusion and address compliance challenges specific to our market while securing sensitive data never leaves the country. It combines global best practices with national sovereignty, making it uniquely suited to Malaysia’s needs.” The FinancialGPT model will be trained exclusively on Malaysia’s financial transaction data to enhance its resilience against cyber threats.
Also Read:
- RBI Forms FREE-AI Committee to Guide Ethical AI Adoption in Indian Financial Sector
- Australian Banks Embrace AI for Enhanced Operations and Customer Service Amidst Evolving Landscape
Beyond this new fraud detection system, BNM is championing wider digital initiatives, including the Digital Asset Innovation Hub. Omar highlighted the hub’s role, stating, “This hub is an important initiative to encourage innovation in a safe environment.” The financial sector has been a frontrunner in digitalization, particularly in banking, payments, and financial services. A survey conducted by the Asian Institute of Chartered Bankers (AICB) revealed that over 70% of financial institutions are already exploring various forms of AI and generative AI. In line with this, the AICB is also developing a framework to guide the responsible adoption of AI among industry players, fostering a secure and innovative financial landscape for Malaysia.
