The application of neural networks to predict abnormal stock returns using insider trading data

Abstract

SUMMARYUntil now, data mining statistical techniques have not been used to improve the prediction of abnormal stock returns using insider trading data. Consequently, an investigation using neural network analysis was initiated. The research covered 343 companies for a period of 4 1 2 years. Study findings revealed that the prediction of abnormal returns could be enhanced in the following ways: (1) extending the time of the future forecast up to 1 year; (2) increasing the period of back aggregated data; (3) narrowing the assessment to certain industries such as electronic equipment and business services and (4) focusing on small and midsize rather than large companies.

How to detect illegal corporate insider trading? A data mining approach for detecting suspicious insider transactions

“…This method finds the relationships among the triggering events within a time sequence to detect suspicious transactions. Safer () performed neural network analysis, which is one of the most important DM tools, in order to measure abnormal stock returns precisely. Goldberg, Kirkland, Lee, Shyr, and Thakker () developed an early detection system for insider trading and other fraudulent activities including misrepresentations of filings and events in stock markets.…”

Multivariate adaptive regression splines and insider trading data for stock prediction

“…The ability of outsiders using insider trading information to predict abnormal returns can be increased by focusing on data such as the size of the company and the number of months in the future that are predictive for stock prices (Seyhun (1986); 80 A. M. SAFER Also, a more mathematically precise analysis using insider trading data for the prediction of abnormal stock returns is now possible. One previous study used a data mining technique, neural networks, to achieve this goal and found that the prediction of abnormal stock returns could thus be enhanced (Safer (2002)). The present study explores the same issue using the very same data, though through the use of a different more recent statistical data mining technique, Multivariate Adaptive Regression Splines (MARS).…”