Stochastic Optimization for Market Return Prediction Using Financial Knowledge Graph

Interactive prediction of financial instrument returns is important. It is needed for asset managers to generate trading strategies as well as for stock exchange regulators to discover pricing anomalies. In this paper, we introduce an integrated stochastic optimization technique, namely genetic programming (GP) with generalized crowding (GC), GP+GC, as an integrated approach for a market return prediction system, using a financial knowledge graph (KG). On the one hand, using time-series data for twenty-nine component stocks of the Dow Jones industrial average, we show that our stochastic local search method can give a better prediction performance by providing a comparison of its return performances with two traditional benchmarks, namely a Buy & Hold strategy and the Moving Average Convergence Divergence (MACD) technical indicator. On the other hand, we use features extracted from a time-evolving knowledge graph constructed from fifty component stocks of the SSE50 Index. These features are used to a GP variant and then incorporate the knowledge extracted from the expression learnt from GP into a KG. Overall, this work demonstrates how to integrate GP+GC with KGs in a powerful manner.

[1]  K. Dejong,et al.  An analysis of the behavior of a class of genetic adaptive systems , 1975 .

[2]  Thomas Stützle,et al.  Stochastic Local Search , 2007, Handbook of Approximation Algorithms and Metaheuristics.

[3]  Viktor de Boer,et al.  The knowledge graph as the default data model for learning on heterogeneous knowledge , 2017, Data Sci..

[4]  Ganesh Mani,et al.  Financial Forecasting Using Genetic Algorithms , 1996, Appl. Artif. Intell..

[5]  M. Valenzuela-Rendón,et al.  Genetic algorithms and Darwinian approaches in financial applications: A survey , 2015, Expert Syst. Appl..

[6]  Franklin Allen,et al.  Using genetic algorithms to find technical trading rules , 1999 .

[7]  Ole J. Mengshoel,et al.  Generalized crowding for genetic algorithms , 2010, GECCO '10.

[8]  Wei Yan,et al.  Learning to optimize profits beats predicting returns -: comparing techniques for financial portfolio optimisation , 2008, GECCO '08.

[9]  Ajith Abraham,et al.  Stock Market Modeling Using Genetic Programming Ensembles , 2006, Genetic Systems Programming.

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

[11]  Ole J Mengshoel,et al.  The Crowding Approach to Niching in Genetic Algorithms , 2008, Evolutionary Computation.

[12]  Samir W. Mahfoud Crowding and Preselection Revisited , 1992, PPSN.

[13]  Frederico G. Guimarães,et al.  An Automated Investing Method for Stock Market Based on Multiobjective Genetic Programming , 2018 .

[14]  Kai Chen,et al.  A LSTM-based method for stock returns prediction: A case study of China stock market , 2015, 2015 IEEE International Conference on Big Data (Big Data).

[15]  Edward R. Pantridge,et al.  TensorFlow enabled genetic programming , 2017, GECCO.

[16]  Tim Kovacs,et al.  Advances in Learning Classifier Systems , 2001, Lecture Notes in Computer Science.

[17]  Ole J. Mengshoel,et al.  Interpretable Categorization of Heterogeneous Time Series Data , 2017, SDM.

[18]  Wolfgang Banzhaf,et al.  Algorithmic Trading with Developmental and Linear Genetic Programming , 2010 .

[19]  R. Palmer,et al.  Time series properties of an artificial stock market , 1999 .

[20]  Fernando Alvarruiz,et al.  Use of an artificial neural network to capture the domain knowledge of a conventional hydraulic simulation model , 2007 .

[21]  Sneha Soni,et al.  Applications of ANNs in Stock Market Prediction : A Survey , 2011 .

[22]  Anthony K. H. Tung,et al.  Similarity evaluation on tree-structured data , 2005, SIGMOD '05.

[23]  Y. Ong,et al.  An empirical study of Genetic Programming generated trading rules in computerized stock trading service system , 2008, 2008 International Conference on Service Systems and Service Management.

[24]  Fikret S. Gürgen,et al.  A comparison of global, recurrent and smoothed-piecewise neural models for Istanbul stock exchange (ISE) prediction , 2005, Pattern Recognit. Lett..