Option Trade Classification

Abstract

We evaluate the performance of common stock trade classification algorithms to infer the trade direction of option trades, a crucial component for many empirical studies in options research. Using a large sample of matched intraday transactions, we show that the algorithms’ success is considerably lower than for stocks. The reason are sophisticated customers who implement their trading strategies via limit orders. We design new rules that improve accuracy by 6% to 47%, depending on the exchanges’ pricing model. In a long-short stock trading strategy based on option order imbalance, our new rules increase the Sharpe ratio from 2.22 to 4.25.

Keywords: buyer/seller initiated trades, trade direction, limit order, Lee and Ready algorithm, quote rule

JEL Classification: C10, G12, G13, G14