Fighting fraud with intelligent algorithms
The Wall Street Journal’s CIO Report recently featured the work of Orange Silicon Valley in piloting deep learning efforts to fight fraud. Led by senior IT architect Xavier Quintuna, the work is fighting offers of cheap calling rates that use IP calling and then drop onto Orange’s networks for the last mile. This type of call fraud uses constantly-changing mobile phone numbers to route traffic. Xavier is using deep learning to identify such number sets to help human agents validate and disable them. The results are then fed back to the deep learning algorithms as a training set. It’s a vivid example of how deep learning can augment work rather than replacing it.
Orange is trying to stop a type of fraud that happens when people illegally use part of Orange’s network for cut-rate telephone calls. “The problem is that the fraud moves so quickly that it has been difficult for Orange’s static algorithms to detect it,” Georges Nahon, CEO of Orange Silicon Valley, a research and development division of the operator, told CIO Journal.
Orange began testing software from startup Skymind that uses deep learning, an advanced form of machine learning, a system designed to better identify patterns and make predictions as its algorithms are exposed to more and more new data. The software sorts through huge quantities of telephone records to recognize changing patterns of fraud.
This is just one part of Orange’s efforts to use artificial intelligence across its IT organization and customer value chain. Here at Orange Silicon Valley we’re fortunate to have access to some of the brightest minds in the Bay Area’s deep learning ecosystem. Stay tuned for more news in this exciting field…