Computational intelligence for analysis concerning financial modelling and the adaptive market hypothesis

This thesis concerns the field of computational intelligence (CI), an important area of computer science that predominantly endeavours to model complex systems with heuristic algorithms. Heuristic algorithms from CI are generally nature or biologically inspired programs that iteratively learn from experience. More specifically, the research focuses on the overlap between the fields of CI and financial analysis, where the financial markets (in the form of financial time series) provide the complex system of interest. Therefore the objective of the thesis can be summarized as a exercise in improving the abilities of CI algorithms for modelling financial time series. CI has been applied to a whole spectrum of domains where techniques are developed at a more general level and then applied to a particular application area or complex system. The financial markets are somewhat unique. Unlike other complex systems in nature, the financial markets are of our own creation and their evolution is a by product of human nature, where the beliefs and bias of the participants (humans) in the complex system (financial markets) govern how the system behaves. This is in contrast to many complex systems where, for example, the opinions of experts have no effect on the outcome. Thus, the motivation of this work is to quantify meaningful characteristics (behaviour) of the financial markets as a means to improve and understand how heuristic algorithms respond to them. This process of applying more scrutiny to the analysis of the application area, yields an approach to algorithm development that takes into account the unique characteristics of the market. To achieve this goal the thesis is structured into three sections that comprise four contribution chapters. The contribution chapters are labelled: validity, implications and innovations and each is motivated by a separate research question. The validity chapter is based on determining a reasonable characterization of the financial markets. This includes a detailed literature review of the popular competing market theories as well as some new innovative tests. There is not a general consensus as to which theory is correct but from a computational intelligence perspective the adaptive market hypothesis (AMH) is revealed as a reasonable characterization of the financial markets and one that provides quantifiable characteristics to be utilized in following chapters. The implications chapter concerns testing the effect of implications of the AMH, if any, on the robustness of models derived from CI. Specifically three implications are examined, i.e., variable stationarity, variable efficiency and the waxing and waning of investment strategies. The experiments concerned six algorithms from four of the major paradigms in supervised learning. The results from each of the studies demonstrated that the implications of the AMH affect CI derived models. This conclusion reveals that the unique properties of the financial markets should be taken into account when applying CI algorithms for modelling and forecasting. The two chapters concerning innovations explore how CI techniques can be improved based on the results from the validity and implications chapters. The first chapter (chapter 6) concerns the development of a meta learner based on the implication of the waxing and waning of investment strategies, the meta learning algorithm called LATIS (Learning Adaptive Technical Indicator System) is a blend of micro and macro modelling perspectives and allows for online adaptive learning with an interpretable white box framework. The second innovations chapter (chapter 7) concerns the discretization of financial time series data into a finite alphabet. A discretization algorithm is developed, which extends an existing state-of-the-art algorithm to handle the characteristics of financial time series. The proposed algorithm, called alSAX (adaptive local Symbolic Aggregate approXimation), is demonstrated to be superior in terms of its symbolic mappings, in relation to a gold standard, and in the popular time series subsequence analysis task. Additionally, an invalid theoretical assumption of the existing algorithm is revealed. The flaw in the algorithm is discussed and its impact is determined based on the characteristics of the time series and the parameters of the algorithm. From the analysis, the thesis offers viable fixes to compensate for the flaw, where the suitability of the fixes are dependent on the problem domain and objective of the data mining task.

[1]  Heikki Mannila,et al.  Rule Discovery from Time Series , 1998, KDD.

[2]  Jiti Gao,et al.  Computer-Intensive Time-Varying Model Approach to the Systematic Risk of Australian Industrial Stock Returns , 2004 .

[3]  Jin Li,et al.  Improving Technical Analysis Predictions: An Application of Genetic Programming , 1999, FLAIRS.

[4]  Knute H Mlott.  Case closed. , 2006, JEMS : a journal of emergency medical services.

[5]  Camillo Lento,et al.  The Profitability Of Technical Trading Rules: A Combined Signal Approach , 2011 .

[6]  Colin Camerer,et al.  The Disposition Effect in Securities Trading: An Experimental Analysis , 1991 .

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

[8]  Nguyen Quoc Viet Hung,et al.  Combining SAX and Piecewise Linear Approximation to Improve Similarity Search on Financial Time Series , 2007, 2007 International Symposium on Information Technology Convergence (ISITC 2007).

[9]  D. Andrews,et al.  Further Evidence on the Great Crash, the Oil-Price Shock, and the Unit-Root Hypothesis , 1992 .

[10]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[11]  H. E. Hurst,et al.  Long-Term Storage Capacity of Reservoirs , 1951 .

[12]  Gordon Leitch,et al.  Economic Forecast Evaluation: Profits versus the Conventional Error Measures , 1991 .

[13]  Li Wei,et al.  Experiencing SAX: a novel symbolic representation of time series , 2007, Data Mining and Knowledge Discovery.

[14]  Benjamin Kuipers,et al.  Designing safe, profitable automated stock trading agents using evolutionary algorithms , 2006, GECCO.

[15]  P. Phillips,et al.  Testing the null hypothesis of stationarity against the alternative of a unit root: How sure are we that economic time series have a unit root? , 1992 .

[16]  O. Rosso,et al.  Complexity-entropy causality plane: A useful approach to quantify the stock market inefficiency , 2010 .

[17]  Sanford J. Grossman.  On the Impossibility of Informationally Efficient Markets , 1980 .

[18]  Adam Smith,et al.  The Wealth of Nations , 1999 .

[19]  Andries P. Engelbrecht.  Heterogeneous Particle Swarm Optimization , 2010, ANTS Conference.

[20]  Stefan Zemke,et al.  Nonlinear index prediction , 1999 .

[21]  Pei-Shan Wu,et al.  Multivariate test of Sharpe–Lintner CAPM with time-varying beta , 2007 .

[22]  Alexandru Todea,et al.  Adaptive Markets Hypothesis - Evidence from Asia-Pacific Financial Markets , 2009 .

[23]  Taufiq Choudhry,et al.  Forecasting the weekly time-varying beta of UK firms: GARCH models vs. Kalman filter method , 2009 .

[24]  Mikio Ito,et al.  Measuring the degree of time varying market inefficiency , 2009 .

[25]  Eamonn J. Keogh,et al.  Probabilistic discovery of time series motifs , 2003, KDD '03.

[26]  Jonathan Timmis,et al.  Artificial Immune Recognition System (AIRS): An Immune-Inspired Supervised Learning Algorithm , 2004, Genetic Programming and Evolvable Machines.

[27]  S. Sosvilla‐Rivero,et al.  Optimization of technical rules by genetic algorithms: evidence from the Madrid stock market , 2005 .

[28]  M. Kaboudan.  Genetic Programming Prediction of Stock Prices , 2000 .

[29]  P. Phillips.  Testing for a Unit Root in Time Series Regression , 1988 .

[30]  Richard Preen.  An XCS approach to forecasting financial time series , 2009, GECCO '09.

[31]  Robert Brooks,et al.  The use of domestic and world market indexes in the estimation of time-varying betas , 2000 .

[32]  L. Lin,et al.  The Applications Of Genetic Algorithms InStock Market Data Mining Optimisation , 2004 .

[33]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[34]  Georg Dorffner,et al.  The benefit of information reduction for trading strategies , 2002 .

[35]  A. Lo.  Long-Term Memory in Stock Market Prices , 1989 .

[36]  Francis X. Diebold,et al.  Unit-Root Tests Are Useful for Selecting Forecasting Models , 1999 .

[37]  P. Perron,et al.  Lag Length Selection and the Construction of Unit Root Tests with Good Size and Power , 2001 .

[38]  Lukas Pichl,et al.  Symbolic analysis of indicator time series by quantitative sequence alignment , 2008, Comput. Stat. Data Anal..

[39]  N. Barberis,et al.  A Model of Investor Sentiment , 1997 .

[40]  Silvano Cincotti,et al.  Clustering of financial time series with application to index and enhanced index tracking portfolio , 2005 .

[41]  Dipankar Dasgupta,et al.  Novelty detection in time series data using ideas from immunology , 1996 .

[42]  Camillo Lento.  Combined signal approach: evidence from the Asian–Pacific equity markets , 2009 .

[43]  Tae Yoon Kim,et al.  Artificial neural networks for non-stationary time series , 2004, Neurocomputing.

[44]  Anil K. Bera,et al.  A test for normality of observations and regression residuals , 1987 .

[45]  R. E. Kalman,et al.  New Results in Linear Filtering and Prediction Theory , 1961 .

[46]  P. D. Jong.  The Diffuse Kalman Filter , 1991 .

[47]  Terence Tai Leung Chong,et al.  An empirical comparison of moving average envelopes and Bollinger Bands , 2003 .

[48]  Kyoji Kawagoe,et al.  Extended SAX: Extension of Symbolic Aggregate Approximation for Financial Time Series Data Representation , 2006 .

[49]  Wu Ze-jun,et al.  An Artificial Immune Model for Abnormal Fluctuation of Stock Price , 2008, 2008 International Symposium on Computational Intelligence and Design.

[50]  Daphne Koller,et al.  Support Vector Machine Active Learning with Applications to Text Classification , 2000, J. Mach. Learn. Res..

[51]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[52]  Jonathan Timmis,et al.  A resource limited artificial immune system for data analysis , 2001, Knowl. Based Syst..

[53]  Sonia Schulenburg,et al.  Portfolio allocation using XCS experts in technical analysis, market conditions and options market , 2007, GECCO '07.

[54]  Tomoharu Nagao,et al.  HXCS and its application to financial time series forecasting , 2006 .

[55]  J. Moody,et al.  Performance functions and reinforcement learning for trading systems and portfolios , 1998 .

[56]  Honghai Liu,et al.  Time Discretisation Applied to Anomaly Detection in a Marine Engine , 2007, KES.

[58]  Eamonn J. Keogh,et al.  Clustering of time-series subsequences is meaningless: implications for previous and future research , 2004, Knowledge and Information Systems.

[59]  John R. Koza,et al.  Genetic programming as a means for programming computers by natural selection , 1994 .

[60]  David F. Hendry,et al.  A Random-Difference Series for Use in the Analysis of Time Series (Journal of the American Statistical Association, vol. 29,934, pp. 11–24 (data cut)) , 1995 .

[61]  Fl Chung,et al.  Financial time series indexing based on low resolution clustering , 2004 .

[62]  M. A. Kaboudan,et al.  A Measure of Time Series’ Predictability Using Genetic Programming , 2004 .

[63]  Craig S. Hakkio,et al.  Conditional variance and the risk premium in the foreign exchange market , 1985 .

[64]  Wolfgang Banzhaf,et al.  Fast and effective predictability filters for stock price series using linear genetic programming , 2010, IEEE Congress on Evolutionary Computation.

[65]  E. Fama.  EFFICIENT CAPITAL MARKETS: A REVIEW OF THEORY AND EMPIRICAL WORK* , 1970 .

[66]  C. Nelson,et al.  Trends and random walks in macroeconmic time series: Some evidence and implications , 1982 .

[67]  Pei-Chann Chang,et al.  Application of Artificial Immune System in Constructing a Financial Early Warning System: An Example of Taiwanese Banking Industry , 2007, Second International Conference on Innovative Computing, Informatio and Control (ICICIC 2007).

[68]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

[69]  Tony Jan,et al.  Machine Learning Techniques and Use of Event Information for Stock Market Prediction: A Survey and Evaluation , 2005, International Conference on Computational Intelligence for Modelling, Control and Automation and International Conference on Intelligent Agents, Web Technologies and Internet Commerce (CIMCA-IAWTIC'06).

[70]  Sanford J. Grossman.  ON THE EFFICIENCY OF COMPETITIVE STOCK MARKETS WHERE TRADES HAVE DIVERSE INFORMATION , 1976 .

[71]  C. L. Giles,et al.  Financial Time Series Forecasting Using K-nearest Neighbors Classiication , 1997 .

[72]  Richard Preen.  Identifying Trade Entry and Exit Timing Using Mathematical Technical Indicators in XCS , 2009, IWLCS.

[73]  A. Lo.  The Adaptive Markets Hypothesis , 2004 .

[74]  G. Schwert,et al.  Heteroskedasticity in Stock Returns , 1989 .

[75]  George Roussos,et al.  Escalation: Complex Event Detection in Wireless Sensor Networks , 2007, EuroSSC.

[76]  J. Lintner.  THE VALUATION OF RISK ASSETS AND THE SELECTION OF RISKY INVESTMENTS IN STOCK PORTFOLIOS AND CAPITAL BUDGETS , 1965 .

[77]  Hitoshi Iba,et al.  Using genetic programming to predict financial data , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[78]  F. Fernández-Rodríguez,et al.  Optimization of technical rules by genetic algorithms: evidence from the Madrid stock market , 2005 .

[79]  M. Hinich.  Testing for dependence in the input to a linear time series model , 1996 .

[80]  Ganapati Panda,et al.  Efficient prediction of stock market indices using adaptive bacterial foraging optimization (ABFO) and BFO based techniques , 2009, Expert Syst. Appl..

[81]  Robert A. Levy,et al.  Conceptual Foundations of Technical Analysis , 1966 .

[82]  Lukas Pichl,et al.  On the Symbolic Analysis of Market Indicators with the Dynamic Programming Approach , 2006, ISNN.

[83]  Michael Kampouridis,et al.  EDDIE for investment opportunities forecasting: Extending the search space of the GP , 2010, IEEE Congress on Evolutionary Computation.

[84]  Jean-Yves Potvin,et al.  Generating trading rules on the stock markets with genetic programming , 2004, Comput. Oper. Res..

[85]  Fazel Naghdy,et al.  Motion segmentation for humanoid control planning , 2008 .

[86]  Aiko M. Hormann,et al.  Programs for Machine Learning. Part I , 1962, Inf. Control..

[87]  Serge Hayward.  Setting up performance surface of an artificial neural network with genetic algorithm optimization: in search of an accurate and profitable prediction of stock trading , 2004, Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753).

[88]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[89]  K. Lim,et al.  Ranking market efficiency for stock markets: A nonlinear perspective , 2007 .

[90]  John H. Holland,et al.  Escaping brittleness: the possibilities of general-purpose learning algorithms applied to parallel rule-based systems , 1995 .

[91]  Eamonn J. Keogh,et al.  iSAX: indexing and mining terabyte sized time series , 2008, KDD.

[92]  George Stephanides,et al.  Improving technical trading systems by using a new MATLAB-based genetic algorithm procedure , 2005, Math. Comput. Model..

[93]  An-Pin Chen,et al.  Using the XCS classifier system for portfolio allocation of MSCI index component stocks , 2011, Expert Syst. Appl..

[94]  Yue Shi,et al.  A modified particle swarm optimizer , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[95]  Russell C. Eberhart,et al.  Multiobjective optimization using dynamic neighborhood particle swarm optimization , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[96]  W. Sharpe.  CAPITAL ASSET PRICES: A THEORY OF MARKET EQUILIBRIUM UNDER CONDITIONS OF RISK* , 1964 .

[97]  Stewart W. Wilson.  Classifier Fitness Based on Accuracy , 1995, Evolutionary Computation.

[98]  A. Tversky,et al.  Prospect theory: an analysis of decision under risk — Source link , 2007 .

[99]  Barney M. Berlin,et al.  Size , 1989, Encyclopedia of Evolutionary Psychological Science.

[100]  Massimo Gastaldi,et al.  The Kalman Filter Approach for Time-varying ß Estimation , 2003 .

[101]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[102]  Jack L. Treynor,et al.  MUTUAL FUND PERFORMANCE* , 2007 .

[103]  Christopher Stone,et al.  Foreign Exchange Trading Using a Learning Classifier System , 2008, Learning Classifier Systems in Data Mining.

[104]  C. Lento,et al.  Investment information content in Bollinger Bands? , 2007 .

[105]  Kuniaki Uehara,et al.  Discover Motifs in Multi-dimensional Time-Series Using the Principal Component Analysis and the MDL Principle , 2003, MLDM.

[106]  Fernando José Von Zuben,et al.  Learning and optimization using the clonal selection principle , 2002, IEEE Trans. Evol. Comput..

[107]  Christopher J. Neely,et al.  Is Technical Analysis in the Foreign Exchange Market Profitable? A Genetic Programming Approach , 1996, Journal of Financial and Quantitative Analysis.

[108]  Stefano Lonardi,et al.  Global detectors of unusual words: design, implementation, and applications to pattern discovery in biosequences , 2001 .

[109]  Michael Kampouridis,et al.  Market fraction hypothesis: A proposed test , 2012 .

[110]  Andrea Frazzini,et al.  The Disposition E ff ect and Underreaction to News , 2006 .

[111]  E. Fama,et al.  Multifactor Explanations of Asset Pricing Anomalies , 1996 .

[112]  Eamonn J. Keogh,et al.  A symbolic representation of time series, with implications for streaming algorithms , 2003, DMKD '03.

[113]  E. Fama,et al.  The Adjustment of Stock Prices to New Information , 1969 .

[114]  John R. Koza,et al.  Genetic programming: a paradigm for genetically breeding populations of computer programs to solve problems , 1990 .

[115]  Pen-Yang Liao,et al.  Dynamic trading strategy learning model using learning classifier systems , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[116]  Peter Ross,et al.  Explorations in LCS Models of Stock Trading , 2001, IWLCS.

[117]  Alex Alves Freitas,et al.  AISEC: an artificial immune system for e-mail classification , 2003, IEEE Congress on Evolutionary Computation.

[118]  Matthew Butler,et al.  Multi-objective optimization with an evolutionary artificial neural network for financial forecasting , 2009, GECCO.

[119]  Tyler Shumway,et al.  Do Behavioral Biases Affect Prices? , 2001 .

[120]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[121]  A. Lo,et al.  Reconciling Efficient Markets with Behavioral Finance: The Adaptive Markets Hypothesis , 2005 .

[122]  A. Lo,et al.  Stock Market Prices Do Not Follow Random Walks: Evidence from a Simple Specification Test , 1987 .

[123]  O. J. Dunn.  Multiple Comparisons among Means , 1961 .