Communications of the ACM
Artificial Intelligence to Tackle Rogue Traders
The University of Sunderland's Computerized Analysis of Stocks and Shares for Novelty Detection of Radical Activities (CASSANDRA) project is developing a software tool to detect financial fraud by combining artificial intelligence with headline analysis to monitor suspicious share trading. The Financial Times reports that as many as 25 percent of U.K. share trades may involve insider trading, and a study by The New York Times suggests as many as 41 percent of North American trades may be affected.
CASSANDRA project manager Dale Addison believes that developing effective anti-fraud methods has never been more important. Addison says the major problem with current anti-fraud systems is false positives. "In contrast, the CASSANDRA system looks at the news stories which may affect a particular company," he says. "So, if two companies are in the process of a merger and someone gets wind that the merger isn't going ahead, a key player will go out and buy or sell stock shares and make a killing on the markets. Using our system that information may be detectable by analysis of news." The CASSANDRA system analyzes the movement of particular stocks and shares for a specific company while accessing headline news from providers such as Reuters, Bloomberg, The Associated Press, and the company's Web site to see what news is available to the company's employees.
From The University of Sunderland
View Full Article
No entries found