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

Authors:
F. Liu;G. S. Ng;C. Quek
Affiliations:
Centre for Computational Intelligence, School of Computer Engineering, Nanyang Technological University, Nanyang Avenue, Singapore 639798, Singapore;Centre for Computational Intelligence, School of Computer Engineering, Nanyang Technological University, Nanyang Avenue, Singapore 639798, Singapore;Centre for Computational Intelligence, School of Computer Engineering, Nanyang Technological University, Nanyang Avenue, Singapore 639798, Singapore
Venue:
Neurocomputing
Year:
2007

Citing 14
Cited 5

Technical Note: \cal Q-Learning

Machine Learning
Contender's network, a new competitive-learning scheme

Pattern Recognition Letters
State space reconstruction parameters in the analysis of chaotic time series—the role of the time window length

Physica D
Wrappers for feature subset selection

Artificial Intelligence - Special issue on relevance
Data equalisation with evidence combination for pattern recognition

Pattern Recognition Letters
Data mining: concepts and techniques

Data mining: concepts and techniques
Neural network learning using entropy cycle

Knowledge and Information Systems
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Time Series Prediction and Neural Networks

Journal of Intelligent and Robotic Systems
A new evolutionary method for time series forecasting

GECCO '05 Proceedings of the 7th annual conference on Genetic and evolutionary computation
A Novel Generic Hebbian Ordering-Based Fuzzy Rule Base Reduction Approach to Mamdani Neuro-Fuzzy System

Neural Computation
Reinforcement learning: a survey

Journal of Artificial Intelligence Research
GA-TSKfnn: Parameters tuning of fuzzy neural network using genetic algorithms

Expert Systems with Applications: An International Journal
A method for segmentation of switching dynamic modes in time series

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Prediction-based portfolio optimization model using neural networks

Neurocomputing
Feature extraction for time-series data: An artificial neural network evolutionary training model for the management of mountainous watersheds

Neurocomputing
A self-organized neuro-fuzzy system for stock market dynamics modeling and forecasting

WSEAS Transactions on Information Science and Applications
A self-organized neuro-fuzzy system for stock market dynamics modeling and forecasting

ICCOMP'10 Proceedings of the 14th WSEAS international conference on Computers: part of the 14th WSEAS CSCC multiconference - Volume II
Fast learning and predicting of stock returns with virtual generalized random access memory weightless neural networks

Concurrency and Computation: Practice & Experience

Quantified Score

Hi-index	0.01

Visualization

Abstract

Time series prediction is traditionally handled by linear models such as autoregressive and moving-average. However they are unable to adequately deal with the non-linearity in the data. Neural networks are non-linear models that are suitable to handle the non-linearity in time series. When designing a neural network for prediction, two critical factors that affect the performance of the neural network predictor should be considered; they are namely: (1) the input dimension, and (2) the time delay. The former is the number of delayed values for prediction, while the latter is the time interval between two data. Prediction accuracy can be improved using suitable input dimension and time delay. A novel method, called reinforcement learning-based dimension and delay estimator (RLDDE), is proposed in this paper to simultaneously determine the input dimension and time delay. RLDDE is a meta-learner that tries to learn the selection policy of the dimension and delay under different distribution of the data. Two benchmarked datasets with different noise levels and one stock price are used to show the effectiveness of the proposed RLDDE together with the benchmarking against other methods.