In this paper by Robert P. Bartlett, Justin McCrary and Maureen O’Hara, these academics use MayStreet data to show how current market practices relating to odd lot quotes result in a large “inside” market where for many stocks better prices routinely exist relative to the National Best Bid or Offer (NBBO). The authors provide strong evidence that being able to see these odd lot quotes provides valuable information to traders with access to proprietary data feeds. The authors develop a XGBoost machine learning prediction algorithm that uses odd lot data to predict future prices, and demonstrate a simple and profitable trading strategy using odd lot data. The authors show that the SEC’s new approach of changing the definition of a round lot reduces, but does not ameliorate, the high incidence of superior odd lot quotes within the NBBO.
To read the full paper, click here.