High-Performance Time Series Prediction With Predictive Error Compensated Wavelet Neural Networks

Burak Berk Ustundag,Ajla Kulaglic

doi:10.1109/access.2020.3038724

Abstract

Machine learning (ML) algorithms have gained prominence in time series prediction problems. Depending on the nature of the time series data, it can be difficult to build an accurate ML model with the proper structure and hyperparameters. In this study, we propose a predictive error compensation wavelet neural network model (PEC-WNN) for improving the prediction accuracy of chaotic and stochastic time series data. In the proposed model, an additional network is used for the prediction of the main network error to compensate the overall prediction error. The main network takes as inputs the time series data through moving frames in multiple-scales. The same structure and hyperparameter sets are applied for quite distinct four types of problems for verification of the robustness and accuracy of the proposed model. Specifically, the Mackey-Glass, Box-Jenkins, and Lorenz Attractor benchmark problems, as well as drought forecasting are used to characterize the performance of the model for chaotic and stochastic data cases. The results show that the PEC-WNN provides significantly more accurate predictions for all compared benchmark problems with respect to conventional machine learning and time series prediction methods without changing any hyperparameter or the structure. In addition, the time and space complexity of the PEC-WNN model is less than all other compared ML methods, including long short-term memory (LSTM) and convolutional neural networks (CNNs).

Highlights

Time series prediction is an important area that has attracted the attention of researchers from different fields, such as business, economics, finance, science, and engineering [1], [2].In this study, we propose an efficient Machine learning (ML) structure for time series prediction problems that provide considerably higher accuracy and low time complexity with respect to conventional algorithms such as long short-term memory (LSTM) networks, and convolutional neural networks (CNNs)
We propose a predictive error compensated wavelet neural network (PEC-WNN) model consisting of two NNs
The data sets are applied to the different models such as simple neural network model, predictive error compensated neural network model (PEC-NN), wavelet neural network (WNN), and predictive error compensated wavelet neural network (PEC-WNN)

Summary

Introduction

We propose an efficient ML structure for time series prediction problems that provide considerably higher accuracy and low time complexity with respect to conventional algorithms such as long short-term memory (LSTM) networks, and convolutional neural networks (CNNs). The main aim of time series prediction is to collect and analyze the past observations of the time series data to develop a model that describes the behavior of the relevant system [1]. The various methods for time series prediction have been developed by using linear models. A conventional statistic methods such as Auto-Regressive (AR) and Autoregressive Integrated Moving Average (ARIMA) assume linear relationships between past values. Development and implementation of linear methods are relatively simple, they are not able to capture non-linear relationships in the data [5]

Results

Discussion

Conclusion