Clustering Structure of Microstructure Measures

20 Pages Posted: 28 Jul 2021 Last revised: 6 Nov 2021

See all articles by Liao Zhu

Liao Zhu

Cornell University - Department of Statistics and Data Science

Ningning Sun

Cornell University - Department of Computer Science

Martin T. Wells

Cornell University - Law School

Date Written: March 15, 2019

Abstract

This paper builds the clustering model of measures of market microstructure features which are popular in predicting the stock returns. In a 10-second time frequency, we study the clustering structure of different measures to find out the best ones for predicting. In this way, we can predict more accurately with a limited number of predictors, which removes the noise and makes the model more interpretable.

Keywords: market microstructure, interpretable machine learning, artificial intelligence in finance, prototype clustering, high-dimensional statistics, dimension reduction

JEL Classification: C10, G10

Suggested Citation

Zhu, Liao and Sun, Ningning and Wells, Martin T., Clustering Structure of Microstructure Measures (March 15, 2019). Cornell Legal Studies Research Paper 21-30, Available at SSRN: https://ssrn.com/abstract=3880751 or http://dx.doi.org/10.2139/ssrn.3880751

Liao Zhu (Contact Author)

Cornell University - Department of Statistics and Data Science ( email )

301 Tower Road
Ithaca, NY 14853-3801
United States
607-379-7330 (Phone)

Ningning Sun

Cornell University - Department of Computer Science

United States

Martin T. Wells

Cornell University - Law School ( email )

Comstock Hall
Ithaca, NY 14853
United States
607-255-8801 (Phone)

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
143
Abstract Views
714
Rank
366,852
PlumX Metrics