Hierarchical Meta-Learning in Time Series Forecasting for Improved Interference-Less Machine Learning

David Afolabi,Ka Man,Sheng-Uei Guan,Xuan Zhao,Prudence Wong

doi:10.3390/sym9110283

Abstract

The importance of an interference-less machine learning scheme in time series prediction is crucial, as an oversight can have a negative cumulative effect, especially when predicting many steps ahead of the currently available data. The on-going research on noise elimination in time series forecasting has led to a successful approach of decomposing the data sequence into component trends to identify noise-inducing information. The empirical mode decomposition method separates the time series/signal into a set of intrinsic mode functions ranging from high to low frequencies, which can be summed up to reconstruct the original data. The usual assumption that random noises are only contained in the high-frequency component has been shown not to be the case, as observed in our previous findings. The results from that experiment reveal that noise can be present in a low frequency component, and this motivates the newly-proposed algorithm. Additionally, to prevent the erosion of periodic trends and patterns within the series, we perform the learning of local and global trends separately in a hierarchical manner which succeeds in detecting and eliminating short/long term noise. The algorithm is tested on four datasets from financial market data and physical science data. The simulation results are compared with the conventional and state-of-the-art approaches for time series machine learning, such as the non-linear autoregressive neural network and the long short-term memory recurrent neural network, respectively. Statistically significant performance gains are recorded when the meta-learning algorithm for noise reduction is used in combination with these artificial neural networks. For time series data which cannot be decomposed into meaningful trends, applying the moving average method to create meta-information for guiding the learning process is still better than the traditional approach. Therefore, this new approach is applicable to the forecasting of time series with a low signal to noise ratio, with a potential to scale adequately in a multi-cluster system due to the parallelized nature of the algorithm.

Highlights

In forecasting time series data, machine learning has been commonly applied in a number of real world scenarios such as stock market prediction, weather/natural phenomena prediction, energy management, human activity classification, control engineering and sign language identification
Other research in the area of time series forecasting have applied a number of techniques including the hidden Markov model [1], support vector regression (SVR) [2], fuzzy logic [3], dynamic time warping [4], and more commonly the artificial neural network (ANN)
Noise in time series forecasting can have a cumulative impairment on the prediction of values n-steps ahead; algorithms that are able to build an accurate model based upon an available data sequence n steps before whilst reducing the impact of high or low frequency noises within the data can be useful in predicting short- or long-term values

Summary

Introduction

In forecasting time series data, machine learning has been commonly applied in a number of real world scenarios such as stock market prediction, weather/natural phenomena prediction, energy management, human activity classification, control engineering and sign language identification. Other research in the area of time series forecasting have applied a number of techniques including the hidden Markov model [1], support vector regression (SVR) [2], fuzzy logic [3], dynamic time warping [4], and more commonly the artificial neural network (ANN) These techniques are able to closely model the training data, but, due to noise within such data, a high error rate can be observed in the test data. Aa more prediction cancan be achieved if other such assuch wind as speed, temperature, moreaccurate accurate prediction be achieved if factors other factors windhumidity speed, and seasonal trends among others are applied as inputs and used to train the artificial neural network humidity and seasonal trends among others are applied as inputs and used to train the artificial in conjunction the temperatures days or weeks

Objectives

Methods

Results

Conclusion