Using Artificial Intelligence to predict insider trading

UW Bothell researcher Solmaz Batebi is studying how Artificial Intelligence can improve the detection of illegal insider trading. Her work found machine learning methods outperformed traditional approaches and sharply reduced the time needed to analyze suspicious trades.

The U.S. Securities and Exchange Commission prosecutes about 50 cases of insider trading on average each year. According to a study from the University of Technology Sydney, the true number of incidents could be at least four times higher. Illegal insider trading involves buying or selling financial securities using information that is not available to the public, and although insiders are required to report their transactions to the SEC, illegal trading remains difficult to detect and even harder to prove.

Solmaz Batebi, an assistant teaching professor in the University of Washington’s School of Business, is exploring Artificial Intelligence as a tool to improve insider trading predictions. Her interest grew from early exposure to financial markets in Iran and later work in market surveillance and regulatory development at the Tehran Stock Exchange, where she helped build data-driven compliance tools and update regulations related to market manipulation and high-frequency trading. That experience pushed her to bridge finance and computer science, combining business knowledge with coding and data science skills.

Batebi later earned a doctorate in Business Administration with a concentration in Finance from the University of Texas Rio Grande Valley and focused her dissertation on whether machines can better predict insider trading. Her research found that machine learning methods substantially outperformed traditional methods in predicting both the likelihood and the magnitude of insider sales. She concluded that human decision making is complex enough that linear models often miss important variables, while Artificial Intelligence is better suited to synthesizing information and identifying behavioral patterns.

The largest benefit was speed. Before Artificial Intelligence, investigations on a single trade could take six months to a year to understand the intention. With Artificial Intelligence, much of that same workload can happen in a couple minutes. Her analysis also found differences in trading behavior across genders: male traders appeared to act more on incentive, while female traders relied more heavily on information. As a result, predictive gains were more pronounced among female insiders.

In fall 2025, Batebi joined UW Bothell, where she teaches finance and brings computer science expertise into the classroom. She encourages students to build technical and analytical skills that can distinguish them in the job market and supports student participation in research. Her next paper will examine how Artificial Intelligence can be applied in investment banking and wealth management.

54

Impact Score

Anu Bradford on tech sovereignty and regulatory fragmentation

Anu Bradford argues that Europe is wavering in its role as the world’s digital rule-setter just as governments everywhere move toward more state control over technology. Global companies are being pushed to treat geopolitical risk, data sovereignty, and Artificial Intelligence governance as core strategic issues.

Mistral launches text-to-speech model

Mistral has expanded its Voxtral family with a text-to-speech system aimed at enterprise voice applications. The company is positioning the open-weights model as a flexible alternative for organizations that want more control over deployment, cost and customization.

UK Parliament opens workforce inquiry on Artificial Intelligence

A UK Parliament committee is examining how Artificial Intelligence is changing business and work, with a focus on both economic opportunity and labour disruption. The inquiry is seeking evidence on government priorities as adoption expands across the economy.

Windows 11 tightens kernel trust for older drivers

Microsoft is changing Windows 11 kernel policy so new drivers must be signed through the Windows Hardware Compatibility Program. Older trusted drivers will still be allowed in some cases to preserve compatibility during the transition.

Contact Us

Got questions? Use the form to contact us.

Contact Form

Clicking next sends a verification code to your email. After verifying, you can enter your message.