Linear and Nonlinear Trading Models with Gradient Boosted Random Forests and Application to Singapore Stock Market

This paper presents new trading models for the stock market and test whether they are able to consistently generate excess returns from the Singapore Exchange (SGX). Instead of conventional ways of modeling stock prices, we construct models which relate the market indicators to a trading decision directly. Furthermore, unlike a reversal trading system or a binary system of buy and sell, we allow three modes of trades, namely, buy, sell or stand by, and the stand-by case is important as it caters to the market conditions where a model does not produce a strong signal of buy or sell. Linear trading models are firstly developed with the scoring technique which weights higher on successful indicators, as well as with the Least Squares technique which tries to match the past perfect trades with its weights. The linear models are then made adaptive by using the forgetting factor to address market changes. Because stock markets could be highly nonlinear sometimes, the Random Forest is adopted as a nonlinear trading model, and improved with Gradient Boosting to form a new technique—Gradient Boosted Random Forest. All the models are trained and evaluated on nine stocks and one index, and statistical tests such as randomness, linear and nonlinear correlations are conducted on the data to check the statistical significance of the inputs and their relation with the output before a model is trained. Our empirical results show that the proposed trading methods are able to generate excess returns compared with the buy-and-hold strategy.

[1]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[2]  Shuzhi Sam Ge,et al.  Linear, adaptive and nonlinear trading models for Singapore stock market with random forests , 2011, 2011 9th IEEE International Conference on Control and Automation (ICCA).

[3]  Lotfi A. Zadeh,et al.  Outline of a New Approach to the Analysis of Complex Systems and Decision Processes , 1973, IEEE Trans. Syst. Man Cybern..

[4]  Vincenzo Pacelli,et al.  Forecasting Exchange Rates: a Comparative Analysis , 2012 .

[5]  M. Dempster,et al.  A real-time adaptive trading system using genetic programming , 2001 .

[6]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[7]  Vincenzo Pacelli,et al.  An Artificial Neural Network Approach for Credit Risk Management , 2011, J. Intell. Learn. Syst. Appl..

[8]  J. Friedman Greedy function approximation: A gradient boosting machine. , 2001 .

[9]  Ll. G. Chambers,et al.  73.52 Spearman’s rank correlation coefficient , 1989 .

[10]  S. Agrawal,et al.  Momentum Analysis based Stock Market Prediction using Adaptive Neuro-Fuzzy Inference System ( ANFIS ) , 2022 .

[11]  Yang Liu,et al.  An introduction to decision tree modeling , 2004 .

[12]  Dimitrios N. Serpanos,et al.  Towards Stock Market Data Mining Using Enriched Random Forests from Textual Resources and Technical Indicators , 2010, AIAI.

[13]  Vitoantonio Bevilacqua,et al.  An Artificial Neural Network Model to Forecast Exchange Rates , 2011, J. Intell. Learn. Syst. Appl..

[14]  P. Sedgwick Spearman’s rank correlation coefficient , 2018, British Medical Journal.

[15]  Wichian Premchaiswadi,et al.  Stock Exchange of Thailand Index Prediction Using Back Propagation Neural Networks , 2010, 2010 Second International Conference on Computer and Network Technology.

[16]  J. Friedman 1999 REITZ LECTURE GREEDY FUNCTION APPROXIMATION: A GRADIENT BOOSTING MACHINE' , 2001 .

[17]  Simon Fong,et al.  The Application of Trend Following Strategies in Stock Market Trading , 2009, 2009 Fifth International Joint Conference on INC, IMS and IDC.

[18]  J. Friedman Stochastic gradient boosting , 2002 .

[19]  R. Edwards,et al.  Technical Analysis of Stock Trends , 1966 .