Fast learning and predicting of stock returns with virtual generalized random access memory weightless neural networks

Authors:
Alberto F. De Souza;Fabio Daros Freitas;André Gustavo Coelho de Almeida
Affiliations:
Departamento de Informática, Universidade Federal do Espírito Santo, Vitória, Espirito SantoBrazil;Receita Federal do Brasil, Vitória, Espirito SantoBrazil;Departamento de Informática, Universidade Federal do Espírito Santo, Vitória, Espirito SantoBrazil
Venue:
Concurrency and Computation: Practice & Experience
Year:
2012

Citing 10
Cited 2

Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Flexible neural trees ensemble for stock index modeling

Neurocomputing
RLDDE: A novel reinforcement learning-based dimension and delay estimator for neural networks in time series prediction

Neurocomputing
A New Intelligent System Methodology for Time Series Forecasting with Artificial Neural Networks

Neural Processing Letters
Face Recognition with VG-RAM Weightless Neural Networks

ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
Prediction-based portfolio optimization model using neural networks

Neurocomputing
Time-series forecasting using flexible neural tree model

Information Sciences: an International Journal
An Introduction to Evolutionary Computation in Finance

IEEE Computational Intelligence Magazine
Financial prediction and trading strategies using neurofuzzyapproaches

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Neural networks and traditional time series methods: a synergistic combination in state economic forecasts

IEEE Transactions on Neural Networks

Special Issue for the Workshop on High Performance Computational Finance

Concurrency and Computation: Practice & Experience
System architecture for on-line optimization of automated trading strategies

WHPCF '13 Proceedings of the 6th Workshop on High Performance Computational Finance

Quantified Score

Hi-index	0.00

Visualization

Abstract

We employ virtual generalized random access memory weightless neural networks, VG-RAM WNN, for predicting future stock returns. We evaluated our VG-RAM WNN stock predictor architecture in predicting future weekly returns of the Brazilian stock market and obtained the same error levels and properties of baseline autoregressive neural network predictors; however, our VG-RAM WNN predictor runs 5000 times faster than autoregressive neural network predictors. This allowed us to employ VG-RAM WNN predictors to build a high frequency trading system able to achieve a monthly return of approximately 35% in the Brazilian stock market. Copyright © 2011 John Wiley & Sons, Ltd.