PSO based Neural Networks vs. Traditional Statistical Models for Seasonal Time Series Forecasting

TL;DR

This study demonstrates that PSO-enhanced neural networks significantly outperform traditional statistical models and standard training methods in seasonal time series forecasting, with improved accuracy across multiple real-world datasets.

Contribution

The paper introduces PSO algorithms to optimize neural network training for seasonal data, showing superior forecasting performance over conventional methods and combining PSO models for further accuracy gains.

Findings

PSO-enhanced neural networks outperform standard BP training.

Neural networks surpass SARIMA, HW, and SVM models in accuracy.

Combining PSO-based models further improves forecasts.

Abstract

Seasonality is a distinctive characteristic which is often observed in many practical time series. Artificial Neural Networks (ANNs) are a class of promising models for efficiently recognizing and forecasting seasonal patterns. In this paper, the Particle Swarm Optimization (PSO) approach is used to enhance the forecasting strengths of feedforward ANN (FANN) as well as Elman ANN (EANN) models for seasonal data. Three widely popular versions of the basic PSO algorithm, viz. Trelea-I, Trelea-II and Clerc-Type1 are considered here. The empirical analysis is conducted on three real-world seasonal time series. Results clearly show that each version of the PSO algorithm achieves notably better forecasting accuracies than the standard Backpropagation (BP) training method for both FANN and EANN models. The neural network forecasting results are also compared with those from the three traditional statistical models, viz. Seasonal Autoregressive Integrated Moving Average (SARIMA), Holt-Winters (HW) and Support Vector Machine (SVM). The comparison demonstrates that both PSO and BP based neural networks outperform SARIMA, HW and SVM models for all three time series datasets. The forecasting performances of ANNs are further improved through combining the outputs from the three PSO based models.