Combining Machine Learning and Agent Based Modeling for Gold Price Prediction

A computational approach combining machine learning (simulated annealing) and agent based simulation is shown to approximate financial time series. The agent based model allows to simulate the market conditions that produced the financial time series and simulated annealing optimize the parameters for the agent based model. The originality of our approach stays in the combination of financial market simulation with meta-learning of its parameters. The original contribution of the paper stays in discussing how the methodology can be applied under several meta-learning conditions and its experimentation on the real world SPDR Gold Trust (GLD) timeseries.

[1]  Peter Ross,et al.  An Adaptive Agent Based Economic Model , 1999, Learning Classifier Systems.

[2]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[3]  Filippo Neri,et al.  PIRR: a methodology for distributed network management in mobile networks , 2008 .

[4]  Filippo Neri,et al.  Case Study on Modeling the Silver and Nasdaq Financial Time Series with Simulated Annealing , 2018, WorldCIST.

[5]  Joshua M. Epstein,et al.  Growing Artificial Societies: Social Science from the Bottom Up , 1996 .

[6]  Filippo Neri,et al.  Intelligent Algorithms Based on Data Processing for Modular Robotic Vehicles Control , 2014 .

[7]  Filippo Neri,et al.  A Matrix Transition Oriented Net for Modeling Distributed Complex Computer and Communication Systems , 2014 .

[8]  Wander Jager,et al.  Artificial Multi-Agent Stock Markets: Simple Strategies, Complex Outcomes , 2006 .

[9]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[10]  Takao Terano,et al.  Analyzing the Influence of Overconfident Investors on Financial Markets Through Agent-Based Model , 2007, IDEAL.

[11]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[12]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[13]  Eric Bonabeau,et al.  Agent-based modeling: Methods and techniques for simulating human systems , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[14]  Graham Kendall,et al.  A Classification of Hyper-heuristic Approaches , 2010 .

[15]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[16]  Leigh Tesfatsion,et al.  Agent-Based Computational Economics: Growing Economies From the Bottom Up , 2002, Artificial Life.

[17]  Yoav Freund,et al.  Automated trading with boosting and expert weighting , 2010 .

[18]  Graham Kendall,et al.  A multi-agent based simulated stock market - testing on different types of stocks , 2003, The 2003 Congress on Evolutionary Computation, 2003. CEC '03..

[19]  Joseph S. Zirilli.  Financial Prediction Using Neural Networks , 1996 .

[20]  Ivan O. Kitov,et al.  PREDICTING CONOCOPHILLIPS AND EXXON MOBIL STOCK PRICE , 2009 .

[21]  Filippo Neri,et al.  A Comparative Study of a Financial Agent Based Simulator Across Learning Scenarios , 2011, ADMI.

[22]  Ganapati Panda,et al.  Prediction of S&P 500 and DJIA stock indices using Particle Swarm Optimization technique , 2008, 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence).

[23]  Filippo Neri,et al.  Agent-based modeling under partial and full knowledge learning settings to simulate financial markets , 2012, AI Commun..

[24]  Filippo Neri,et al.  Learning and Predicting Financial Time Series by Combining Natural Computation and Agent Simulation , 2011, EvoApplications.

[25]  Blake LeBaron,et al.  Agent-based computational finance : Suggested readings and early research , 2000 .