Compliance tech and data analytics provider SteelEye plans to address market abuse and communications monitoring with lexicon technology. The new tech can reportedly monitor over 6x as many search terms as a typical lexicon.
SteelEye’s product has been developed in a manner that adheres to stricter regulations and the rising numbers of communications channels.
In the past, financial institutions have depended on technology that scans or monitors internal communications for certain words and sequences of words in order to find cases of potential misconduct or market abuse activities. However, its limited search capacity and irrelevant matches have led to a fairly large number of false positives.
The lexicon created by SteelEye aims to cover thousands of key search terms in order to capture linguistic variations, colloquialisms, “text-speak”, abbreviations, and typos. The lexicon also uses artificial intelligence algorithms to filter for context and to eliminate the reporting of false positives.
Even though many firms are adopting policies that prohibit the use of alternative communications channels, such as Whatsapp, traders can still use these avenues to communicate. The data analytics companies deal with this by flagging the particular context of messages and then the intent to potentially take an illicit conversation to an unmonitored communication channel.
It does this by identifying comments like “Let’s talk on WhatApp” or “I’ll text you” – phrases which would not typically be flagged by regular tools as ‘Whatsapp’ is not usually included in the older lexicon, nor is the option to differentiate between the abbreviated ‘I’ll’ from ‘I will.’
Matt Storey, Chief Product Officer at SteelEye, stated:
“One of the main reasons legacy lexicons trigger such vast volumes of false positives is because they don’t consider the context in which a communication takes place. As a result, many firms have ended up limiting themselves to a small number of search terms to reduce the number of alerts triggered. However, in doing so, they risk missing key signs of market abuse.”
Storey added:
“Our new lexicon completely solves this problem by not only accounting for an unparalleled degree of linguistic variety – but also introducing AI to determine the context of how and where a piece of communication took place. These two fundamental changes enable firms to monitor for a much wider range of risks and greatly reduce the number of false positives.”
SteelEye intends to further develop advanced capabilities for the product. For instance, if a worker usually has phone conversations of over 2 minutes and then makes a 10-second call, with “uncharacteristic intonation” – where they only say something like, “check WhatsApp”, the technology will be able to take that reference to an unmonitored channel with the unusual call duration to generate a clearer picture of what’s actually taking place.
Storey also mentioned:
“Lexicons are and will remain important to help firms detect signs of wrongdoing. The industry must focus on getting them right by thinking about searching for language, meaning, and intent rather than individual words or phrases.”
