Bharti Airtel’s artificial intelligence (AI)-powered spam detection system has identified 112 million potential spam calls and three million text messages in Tamil Nadu within 12 days of its launch.
The system uses an algorithm to identify and classify calls and SMSes as ‘suspected spam’ by analysing parameters such as usage patterns, call frequency, and call duration. The system has two filters: one at the network layer and the other at the information technology systems. In two milliseconds, the system processes 1.5 billion messages and 2.5 billion calls, equivalent to processing 1 trillion records using AI.
The system also alerts customers to malicious links received via SMS through a centralised database of blacklisted uniform resource locator (URLs) and real-time scanning of every SMS by a state-of-the-art AI algorithm. The system can also detect anomalies such as frequent changes in IMEI, which typically indicate fraudulent behaviour.
By layering these protective measures, Airtel ensures its customers receive the maximum level of defense against the evolving landscape of spam and fraud threats.
