Forecasting seasonal time series using weighted gradient RBF network based autoregressive model

Files

hdl_108661.pdf (657.62 KB)
  (Restricted Access)

Date

2016

Authors

Ruan, W.
Sheng, Q.
Xu, P.
Tran, N.
Falkner, N.
Li, X.
Zhang, W.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Conference paper

Citation

Proceedings of the 25th International Conference on Information and Knowledge Management, 2016, vol.24-28-October-2016, pp.2021-2024

Statement of Responsibility

Wenjie Ruan, Quan Z. Sheng, Peipei Xu, Nguyen Khoi Tran, Xue Li, Wei Emma Zhang

Conference Name

25th ACM International Conference on Information and Knowledge Management (CIKM) (24 Oct 2016 - 28 Oct 2016 : Indianapolis, IN)

Abstract

How to accurately forecast seasonal time series is very important for many business area such as marketing decision,planning production and profit estimation. In this paper, we propose a weighted gradient Radial Basis Function Network based AutoRegressive (WGRBF-AR) model for modeling and predicting the nonlinear and non-stationary seasonal time series. This WGRBF-AR model is a synthesis of the weighted gradient RBF network and the functional-coefficient autoregressive (FAR) model through using the WGRBF networks to approximate varying coefficients of FAR model. It not only takes the advantages of the FAR model in nonlinear dynamics description but also inherits the capability of the WGRBF network to deal with non-stationarity. We test our model using ten-years retail sales data on five different commodity in US. The results demonstrate that the proposed WGRBF-AR model can achieve competitive prediction accuracy compared with the state-of-the-art.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

© 2016 ACM

License

Grant ID

Call number

Persistent link to this record