Subscribe to our mailing list

* indicates required







We seek to provide information, insights and direction that may enable the Financial Community to effectively and efficiently operate in a regulatory risk-free environment by curating content from all over the web.


Stay Informed with the latest fanancialish news.





Bad Behavior AI Database Targets Rogue Traders Before They Act

March 8, 2017

Trader surveillance has come a long way, baby. And while few people would admit to liking or appreciating any form of surveillance, the type of oversight that you'll read about here can be viewed oversight can be downright intrusive and offensive.


Let's start off by asking: What's there to dislike about young, ambitious, nose-to-the-grindstone traders who work long hours after the market close and on weekends, and offer inspired trading ideas to their colleagues?


Well, in this brave new world of trader surveillance, such a person may be considered a potential rogue trader - that's according former Goldman Sachs research analyst Erkin Adylov, who's building a library of banking villainy based on the behaviors of hundreds of past villianous traders, like UBS's Tom Hayes and SocGen’s Jerome Kerviel. Using inputted data, from stress levels in voice recordings to the frequency of visits to the staff lunchroom, Adylov and his team at startup Behavox grade employees on how likely they are to go bad before they do anything wrong.


DEMAND FOR THEIR SERVICES.    Some Wall Street firms are currently using the Behavox software program, and some big investment banks and commodities dealers reportedly have begun testing it. This should not come as a surprise - firms can tolerate just so many large fines and elephantine trading losses that are difficult to prevent or even detect. 


“If you don’t know what your employees are doing, then you’re vulnerable. Some banks don’t seem to want to know how exposed they are, and they are the ones who are going to get fined next.” - - Adylov.  


ARTIFICIAL INTELLIGENCE.    Behavox uses machine learning to scrutinize every aspect of an employee’s working life. The technology enables computers to teach themselves how to collate and analyze huge volumes of data. Behavox scans petabytes of data, flagging anything that deviates from the norm for further investigation. That could be something as seemingly innocuous as shouting on a phone call, accessing a work computer in the middle of the night, or visiting the restroom more than colleagues. The system checks these behaviors against case studies of past traders who have strayed from the straight and narrow and looks for a match.


CONDUCT RISK EXCHANGE.    While other companies use similar technology to watchdog trading floors, Behavox takes it one step further, compiling a central repository of behavioral patterns accessible to all clients. Adylov calls it the Conduct Risk Exchange. His challenge is to persuade firms to share potentially embarrassing details about their inner workings. If he can build a network big enough - more than the 3 companies that have signed up so far - it could change the way banks police themselves.