A Network-Based Model for Optimizing Returns in the Stock Market

Complex network has been proven a powerful tool in data analysis and machine learning due to its ability for characterizing dynamical properties and arbitrary range (from local to global) of relationships of data. In this paper we introduce a network-based model aiming to maximize the returns in stock market trading operations. It works as semi-supervised learning techniques with two phases: 1) A training phase, in which it maps the price variation ranges into nodes of a network and identify possible price oscillation trend patterns among these ranges, based on the topological structure; 2) An operating phase, in which it then performs buying and selling operations according to the identified patterns. We assess the model by testing its performance on historical data from 10 of the most traded stocks from the Brazilian Stock Exchange and the obtained results are promising, with the model's best returns being able to outperform the stock price returns for the same period in 7 out of the 10 cases under consideration.

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

[2]  Huajiao Li,et al.  Transmission of linear regression patterns between time series: from relationship in time series to complex networks. , 2014, Physical review. E, Statistical, nonlinear, and soft matter physics.

[3]  M E J Newman,et al.  Fast algorithm for detecting community structure in networks. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[4]  Luciano Rossoni,et al.  Models and methods in social network analysis , 2006 .

[5]  Dong-Hong Ji,et al.  Time series trend detection and forecasting using complex network topology analysis. , 2019, Neural networks : the official journal of the International Neural Network Society.

[6]  Liang Zhao,et al.  Detecting Time Series Periodicity Using Complex Networks , 2014, 2014 Brazilian Conference on Intelligent Systems.

[7]  Aderemi Oluyinka Adewumi,et al.  Comparison of ARIMA and Artificial Neural Networks Models for Stock Price Prediction , 2014, J. Appl. Math..

[8]  Réka Albert,et al.  Structural vulnerability of the North American power grid. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.

[9]  O. Sporns.  Network Analysis , Complexity , and Brain Function , 2002 .

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

[11]  J. Montoya,et al.  Small world patterns in food webs. , 2002, Journal of theoretical biology.

[12]  Mark Newman,et al.  Networks: An Introduction , 2010 .

[13]  F. Hayek.  The economic nature of the firm: The use of knowledge in society , 1945 .

[14]  Shouyang Wang,et al.  Forecasting stock market movement direction with support vector machine , 2005, Comput. Oper. Res..

[15]  Toyotaro Suzumura,et al.  Finding overlapping communities in multilayer networks , 2018, PloS one.

[16]  James H. Brown,et al.  A general model for the structure and allometry of plant vascular systems , 1999, Nature.

[17]  Liang Zhao,et al.  Handwritten Data Clustering Using Agents Competition in Networks , 2012, Journal of Mathematical Imaging and Vision.

[18]  Michalis Faloutsos,et al.  On power-law relationships of the Internet topology , 1999, SIGCOMM '99.

[19]  Olaf Sporns,et al.  Networks analysis, complexity, and brain function , 2002 .

[20]  Liang Zhao,et al.  High-level pattern-based classification via tourist walks in networks , 2015, Inf. Sci..

[21]  Dong-Hong Ji,et al.  A Network-Based High Level Data Classification Technique , 2018, 2018 International Joint Conference on Neural Networks (IJCNN).