AI, Behavioral Analytics & Holistic Approaches to Surveillance

Traders Magazine Online News, February 12, 2018

John D'Antona Jr.

Market abuse - how can we diagnose and prevent it?

One firm, Opimas, thinks it can shed light on the subject. The firm recently released a report, "Fighting Market Abuse: AI, Behavioral Analytics & Holistic Approaches to Surveillance," which found that the use of AI and other technologies in surveillance has the potential to produce more intelligent alerts, improve automation, and reduce the manpower needed to manage investigations. AI and behavioral analytics also have the potential to preemptively identify suspicious behavior before any damages are incurred.

This marks a significant departure for market participants that have largely relied on reactive, threshold-based alerts designed to primarily satisfy regulatory requirements. At present, most surveillance is conducted in a siloed manner, with separate systems creating alerts of suspicious behaviors for each communication channel and asset class. This is no longer sufficient, and the evolution in trade and communications surveillance is inevitable, for myriad reasons and with compelling benefits.

Key findings of the Market Surveillance report include the following:

• Market participants are now firmly focused on surveillance approaches that reduce costs by improving the quality of alerts and automate investigations. With false alert reduction as the primary driver, institutional spending on technology is expected to rise—up to US$1.4 billion by 2021.

• Surveillance headcount reduction will start to be visible in 2019 as the use of artificial intelligence and rationalization gather momentum at Tiers 1, 2 and 3 sell-side firms, Tiers 1 and 2 buy-side firms, exchanges, and regulators.

• Regulations—Dodd-Frank, MiFID II, Market Abuse Regulation and General Data Privacy Regulation, among others—that aim to protect investors from market manipulation are increasing in scope and severity, so trade surveillance is steadily moving forward as a priority for market participants. 

• Total fines for market manipulation hit a high point in 2015, reaching nearly US$9 billion, but Opimas expects noncompliance with MiFID II to be cited for market misconduct fines as well, now that the regulation is in effect.

• While the threats of individual lawsuits for misuse of private data already make financial institutions nervous, the official fine schedule for GDPR is eye-popping: A single infraction threatens up to 4% of annual global turnover or €20 million, whichever amount is bigger.

• About 80% of trade and communications alerts currently rely on static rules-based thresholds. By 2022, Opimas expects this figure to halve, and be supplanted by more intelligent alerting methodologies. Some of the solutions already being sold to the market include K-means clustering, support vector machines, neural networks, relationship mapping, behavioral analytics, as well as holistic approaches.

• Market participants must contend with and evaluate appropriate management of trade and order data, e-communications, voice and mobile surveillance. 

The full report is available from Opimas.

For more information on related topics, visit the following channels:

• Regulations
• Technology
• Equities