iTrade: An Adaptive Risk-Adjusted Intelligent Stock Trading System from the Perspective of Concept Drift

In China stock market, more than 95% are non-professional investors. Due to the lack of professional skill and the complexity of financial indicators and the varying investment environment, non-professional investors are in great need of a data mining-based intelligent stock trading decision-support system. Considering the existence of concept drift phenomenon, this study proposes an adaptive learning process with the Lasso algorithm-based feature selection. Moreover, we use support vector machine as stock market predictor for stock selection and a risk-adjusted method for portfolio optimization. Finally, a web-based Adaptive Risk-adjusted Intelligent Stock Trading System (iTrade) is established. The seven-year (2005-2011) back-testing shows that our system can generate much higher cumulative return than the benchmark (Shanghai Composite Index) in China stock market. Meanwhile, concept drift analysis of adaptive relevant variable discovery process has revealed contrasting historical trends between two selected industries. In conclusion, the iTrade is suitable for non-professional investors in portfolio management, following the varying stock market environment and providing effective guidance.

[1]  Mehdi R. Zargham,et al.  A Decision Tree-based Classification Approach to Rule Extraction for Security Analysis , 2006, Int. J. Inf. Technol. Decis. Mak..

[2]  Shingo Mabu,et al.  A portfolio optimization model using Genetic Network Programming with control nodes , 2009, Expert Syst. Appl..

[3]  Padraig Cunningham,et al.  A case-based technique for tracking concept drift in spam filtering , 2004, Knowl. Based Syst..

[4]  Indre Zliobaite,et al.  Learning under Concept Drift: an Overview , 2010, ArXiv.

[5]  Fabio Roli,et al.  Stock Market Prediction by a Mixture of Genetic-Neural Experts , 2002, Int. J. Pattern Recognit. Artif. Intell..

[6]  David Enke,et al.  The adaptive selection of financial and economic variables for use with artificial neural networks , 2004, Neurocomputing.

[7]  Cun-Hui Zhang,et al.  Adaptive Lasso for sparse high-dimensional regression models , 2008 .

[8]  Philip S. Yu,et al.  Mining concept-drifting data streams using ensemble classifiers , 2003, KDD '03.

[9]  Chang-Chun Lin,et al.  Genetic algorithms for portfolio selection problems with minimum transaction lots , 2008, Eur. J. Oper. Res..

[10]  J. Lewellen.  The Cross Section of Expected Stock Returns , 2014 .

[11]  Ludmila I. Kuncheva,et al.  Classifier Ensembles for Detecting Concept Change in Streaming Data: Overview and Perspectives , 2008 .

[12]  Chien-Feng Huang,et al.  A hybrid stock selection model using genetic algorithms and support vector regression , 2012, Appl. Soft Comput..

[13]  Josef Lakonishok,et al.  Corporate Governance through the Proxy Contest: Evidence and Implications , 1993 .

[14]  Kuang Yu Huang,et al.  A hybrid model for stock market forecasting and portfolio selection based on ARX, grey system and RS theories , 2009, Expert Syst. Appl..

[15]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[16]  Žliobait . e,et al.  Learning under Concept Drift: an Overview , 2010 .

[17]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[18]  Byoung-Tak Zhang,et al.  Adaptive stock trading with dynamic asset allocation using reinforcement learning , 2006, Inf. Sci..

[19]  Weili Lin,et al.  An Intelligent Model for Stock Investment with Buffett Strategy, Classifier System, Neural Networkand Linear Programming , 2004, ICEB.

[20]  Se-Hak Chun,et al.  Dynamic adaptive ensemble case-based reasoning: application to stock market prediction , 2005, Expert Syst. Appl..

[21]  Kuang Yu Huang,et al.  Application of VPRS model with enhanced threshold parameter selection mechanism to automatic stock market forecasting and portfolio selection , 2009, Expert Syst. Appl..

[22]  Fenghua Wang,et al.  What Determines Chinese Stock Returns? , 2003 .

[23]  Mohammed Omran,et al.  Linear Versus Non‐linear Relationships Between Financial Ratios and Stock Returns: Empirical Evidence from Egyptian Firms , 2004 .

[24]  Chih-Fong Tsai,et al.  Combining multiple feature selection methods for stock prediction: Union, intersection, and multi-intersection approaches , 2010, Decis. Support Syst..

[25]  WangFenghua,et al.  What Determines Chinese Stock Returns , 2006 .

[26]  Sandip Mukherji,et al.  A Fundamental Analysis of Korean Stock Returns , 1997 .

[27]  Ronnie Sadka,et al.  Predictability and the Earnings-Returns Relation , 2008 .

[28]  Andreas Christmann,et al.  Support vector machines , 2008, Data Mining and Knowledge Discovery Handbook.