Many trading firms have been charged with insufficient supervision of trading activities of their own traders. Recently a large wall street firm was charged with hundreds of millions of dollars of fine for insufficient fraud detection controls that allowed spoofing practice in one of their trading desks to go on for years. Trading patterns such as spoofing, layering, front running etc. are considered fraudulent trading patterns. Trading firms are expected to have controls that detect such trading behaviors by both their own traders and by their clients. Fraudsters employ different techniques, often even using sophisticated technology like a trading algorithm to mask the fraudulent nature of their trading behavior.
In this use case scenario, we consider a hypothetical example of a trader wanting to buy a stock at a lower price than the current price of the stock. This trader would try to move the market towards his/her desired bid price by placing a lot of sell orders a few ticks away from the best offer and creating sell pressure on the stock and thereby moving the price lower. This is illegal and should be detected by the trading firm using their fraud detection controls. Once the price is in their price range, the trader would cancel all their sell orders and execute their buy order. A similar case of spoofing can also occur if the trader wants to sell their position at a higher price and moves the market higher using spoofing orders. In this hypothetical example, trader has applied spoofing techniques to profit from those trades, Eventually the regulatory authorities caught up with the traders and found them guilty of fraud and fined the trading firm a large sum as fines and restitution for the losses they caused for other investors.
EagleAi Fraud Risk module looks for patterns of fraud from transaction logs, such as spoofing and layering on trading activities of clients and traders. It looks for patterns of buy orders and sell orders placed by the traders on every symbol and check if they follow the fraudulent trading patterns. If it detects such patterns, it alerts the risk managers with contextual data to aid in further investigation. Timely report from EagleAi would help the risk managers to identify such issues early on that could lead to taking corrective actions at the earliest. This not only prevents leakages of hundreds of millions of dollars as fines but also prevents the firm from any reputational damages.
- Introduction to EagleAi TradeWatch
- EagleAi Use Case Series: Compliance Risk – A junior developer accidentally removes critical compliance checks which goes unnoticed for a very long time
- EagleAi Use Case Series: Market Data Risk – Bad market data causes a broker to reject orders from a client incorrectly which leads to a financial loss
- EagleAi Use Case Series: Trading Risk – A single order with incompatible instructions from a client caused $100k+ loss in revenues for a major broker