Mumbai: The central bank's upcoming Digital Payments Intelligence Platform ( DPIP) would harness AI to detect and prevent payment frauds in real time, officials aware of the initiative told ET.
In its first phase, the Reserve Bank of India ( RBI) has built a negative registry that integrates data from telecom operators and the Indian Cyber Crime Coordination Centre (I4C) to flag suspicious or fraudulent entities, said officials.
"The RBI has developed this AI-driven platform through its innovation hub, which is now being implemented across several banks," said an official in the know. "In the pilot stage, banks are sharing data through this platform, which is becoming increasingly effective in identifying fraud-related patterns and is being replicated across other banks." At the beginning of this year, the RBI onboarded five banks onto the digital intelligence platform, which is now being scaled up to include more than a dozen lenders.
In the next phase to be rolled out soon, the AI-driven platform will analyse transactions and assign instant risk scores, enabling banks to take preventive measures such as enhanced due diligence, additional verification, or temporary debit freezes when potential fraud is detected.
In the second phase, which will be launched shortly, banks will begin sharing fraud-related data with the platform in real time.
"This is going to be a much bigger platform where the AI-based models would start alerting banks that a transaction could be a potential fraud, prompting them to carry out enhanced due diligence or take actions such as a debit freeze," said another banking official aware of the matter.
During the monetary policy announcement on October 1, the RBI said it is preparing to operationalise the DPIP, which will leverage AI to flag risky transactions and curb digital fraud.
"We are now implementing the Digital Payments Intelligence Platform; the actual prototype is being developed by our innovation hub," RBI Deputy Governor T. Rabi Sankar had said. "An entity is being set up to run this. The basic idea is to collect information from multiple sources-mule accounts, telecom, geographical location, and more-and train an AI system on this data."
Sankar explained that the system will generate pre-transaction alerts if it identifies a risk, allowing banks or customers to decide whether to proceed.
In FY25, banks reported 13,516 cases of card and internet frauds amounting to Rs 520 crore. Most of these occurred through digital channels such as cards and internet banking. While private sector banks accounted for the majority of digital frauds, public sector lenders reported most of the incidents linked to their loan books.
In its first phase, the Reserve Bank of India ( RBI) has built a negative registry that integrates data from telecom operators and the Indian Cyber Crime Coordination Centre (I4C) to flag suspicious or fraudulent entities, said officials.
"The RBI has developed this AI-driven platform through its innovation hub, which is now being implemented across several banks," said an official in the know. "In the pilot stage, banks are sharing data through this platform, which is becoming increasingly effective in identifying fraud-related patterns and is being replicated across other banks." At the beginning of this year, the RBI onboarded five banks onto the digital intelligence platform, which is now being scaled up to include more than a dozen lenders.
In the next phase to be rolled out soon, the AI-driven platform will analyse transactions and assign instant risk scores, enabling banks to take preventive measures such as enhanced due diligence, additional verification, or temporary debit freezes when potential fraud is detected.
In the second phase, which will be launched shortly, banks will begin sharing fraud-related data with the platform in real time.
"This is going to be a much bigger platform where the AI-based models would start alerting banks that a transaction could be a potential fraud, prompting them to carry out enhanced due diligence or take actions such as a debit freeze," said another banking official aware of the matter.
During the monetary policy announcement on October 1, the RBI said it is preparing to operationalise the DPIP, which will leverage AI to flag risky transactions and curb digital fraud.
"We are now implementing the Digital Payments Intelligence Platform; the actual prototype is being developed by our innovation hub," RBI Deputy Governor T. Rabi Sankar had said. "An entity is being set up to run this. The basic idea is to collect information from multiple sources-mule accounts, telecom, geographical location, and more-and train an AI system on this data."
Sankar explained that the system will generate pre-transaction alerts if it identifies a risk, allowing banks or customers to decide whether to proceed.
In FY25, banks reported 13,516 cases of card and internet frauds amounting to Rs 520 crore. Most of these occurred through digital channels such as cards and internet banking. While private sector banks accounted for the majority of digital frauds, public sector lenders reported most of the incidents linked to their loan books.
You may also like
Lalu IRCTC scam 'fountainhead', says court as it frames charges
Gaza deal: Trump signs peace plan, hostages exchanged, Israeli troops return — what's next?
National Commission for Women flags lapses, seeks fast-track trial
Governer: Don't have confidence to say West Bengal is safe
Keir Starmer savaged over 'big fat socialist dreams' in digital ID takedown
