A binary ensemble classifier for high-frequency trading

The aim of this study was to model and use machine learning techniques to maximize the chance of a market maker be executed successfully in a stock market, that is, when their bid and ask orders are filled at the desired prices. In this context, a binary ensemble classifier was created to decide whether, at a specific time, is or not propitious to start a new market making process. Conducting the study over a large volume of data for high-frequency traders, we showed that the new proposed ensemble classifier was able to improve the efficiency of the isolated models and the precision of the models are better than random decision makers.