RBIH chief executive Rajesh Bansal said that the AI platform, called Mulehunter.Ai, has already been deployed by two large public sector banks so far
Bansal added that percentage of accuracy of the new AI tool is three times than that of previous manual systems of banks
The AI tool was developed after identifying 19 patterns, including sudden transactions in a dormant account, multiple credits in an account followed by one large debit, among others
The Reserve Bank of India’s (RBI) innovation arm is reportedly in discussions with 10 public and private sector banks to accelerate the adoption of its artificial intelligence (AI)-powered platform to detect cases of financial fraud via “mule accounts”.
Mule accounts refers to bank accounts used for illegal activities such as money laundering, fraud, and other illegal operations.
Reserve Bank Innovation Hub’s (RBIH) chief executive Rajesh Bansal told Economic Times that the AI platform, called Mulehunter.Ai, has already been deployed by two large public sector banks. He added that early results from the deployment of the tool have been “encouraging in terms of far better accuracy and cutting down the time taken”.
“If the percentage of accuracy of the manual system was X, this is 3X. If the time taken was Y, this is 0.1Y,” Bansal said.
The RBIH chief executive said that the AI tool was developed after identifying 19 patterns, including sudden transactions in a dormant account, multiple credits in an account followed by one large debit, among others.
These patterns were identified after the RBIH conducted stakeholder consultations with as many as 10 banks to ascertain the traditional approach adopted by lenders while flagging mule accounts.
The insights gathered from the meeting revealed that most banks still used a rule-based system. Under this, suspected accounts were first identified and then verification was done manually in each case, which led to significant loss of time.
However, the new AI platform has been envisaged to speed up the detection of fraudulent accounts. “The best way would be to look at where the money eventually goes–to mule accounts,” said Bansal, adding that there are multiple channels via which frauds can occur and the sum involved can be as much as INR 1 Cr “these days”.
The comments come months after RBI governor Shaktikanta Das, in July this year, urged public and private sector banks to shore up their security measures to crack the whip on mule accounts and digital frauds.
Thereafter in October, reports surfaced that the central bank was looking to develop an AI-enabled system to alert individuals in real-time about financial fraud and enable banks and financial institutions to detect mule accounts.
As per government data, Indians lost as much as INR 11,333 Cr to cyber fraud in just the first nine months of 2024. Just days ago, minister of state for finance, Pankaj Chaudhary, informed the Parliament that the country saw 6.32 Lakh cases of UPI frauds worth INR 485 Cr in the first six months of the ongoing financial year 2024-25 (FY25)
