Recognizing Informed Option Trading
This work demonstrates the ability to recognize a certain class of informed trading exists which is based on private information that cannot be efficiently discounted into stock prices using machine learning algorithms and the rich features available for option markets.
Abstract
While equity (stock) markets are generally efficient in discounting public information into stock prices, we believe that in option markets a certain class of informed trading exists which is based on private information that cannot be efficiently discounted into stock prices. This kind of trade, made either by insiders or large institutions with the resources to deduce non-public information about a stock, allows participants to make bets with a limited downside risk and enormous upside potential. We demonstrate the ability to recognize this class of trades using machine learning algorithms and the rich features available for option markets. We present a simple trading strategy that buys a portfolio of selected options and show that it generates outstanding returns.