Evolution of High Frequency Systematic Trading: A Performance-Driven Gradient Boosting Model

Quantitative Finance

18 Pages Posted: 7 Sep 2017

See all articles by Nan Zhou

Nan Zhou

Quest Partners LLC

Wen Cheng

Pennsylvania State University - Department of Mathematics

Yichen Qin

University of Cincinnati - Department of Business Analytics

Zongcheng Yin

Anhui Agricultural University

Date Written: September 10, 2013

Abstract

This paper proposes a performance-driven gradient boosting model (pdGBM) which predicts short-horizon price movements by combining nonlinear response functions of selected predictors. This model performs gradient descent in a constrained functional space by directly minimizing loss functions customized with different trading performance measurements. To demonstrate its practical applications, a simple trading system was designed with trading signals constructed from pdGBM predictions and fixed holding period in each trade. We tested this trading system on the high-frequency data of SPDR S&P 500 index ETF (SPY). In the out-of-sample period, it generated an average of 0.045% return per trade and an annualized Sharpe ratio close to 20 after transaction costs. Various empirical results also showed the model robustness to different parameters. These superior performances confirm the predictability of short-horizon price movements in the US equity market. We also compared the performance of this trading system with similar trading systems based on other predictive models like the gradient boosting model with L2 loss function and the penalized linear model. Results showed that pdGBM substantially outperformed all other models by higher returns in each month of the testing period. Additionally, pdGBM has many advantages including its capability of automatic predictor selection and nonlinear pattern recognition, as well as its simply structured and interpretable output function.

Keywords: Gradient Boosting, High Frequency, TAQ, Systematic Trading, Predictability

JEL Classification: C4 C8 G1

Suggested Citation

Zhou, Nan and Cheng, Wen and Qin, Yichen and Yin, Zongcheng, Evolution of High Frequency Systematic Trading: A Performance-Driven Gradient Boosting Model (September 10, 2013). Quantitative Finance. Available at SSRN: https://ssrn.com/abstract=2323899

Nan Zhou (Contact Author)

Quest Partners LLC ( email )

126 East 56th Street 19th Floor
New York, NY 10022
United States

Wen Cheng

Pennsylvania State University - Department of Mathematics ( email )

University Park
State College, PA 16802
United States

HOME PAGE: http://www.math.psu.edu/cheng

Yichen Qin

University of Cincinnati - Department of Business Analytics ( email )

606 Carl H. Lindner Hall 2925 Campus Green Drive
PO Box 210211
Cincinnati, OH 45221-0211
United States

Zongcheng Yin

Anhui Agricultural University ( email )

130 Changjiang W Rd, Shushan Qu
Hefei, Anhui 230031
China

Register to save articles to
your library

Register

Paper statistics

Downloads
193
rank
154,115
Abstract Views
579
PlumX Metrics