An intelligent model for predicting demand pattern

Wai Keung Wong; Z. X. Guo

An intelligent model for predicting demand pattern

The Hong Kong Polytechnic University

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

Abstract

To handle the seasonal product demand forecasting problem, this paper develops an intelligent forecasting model integrating a harmony search algorithm, an extreme learning machine (ELM) and a heuristic finetuning process. The ELM combined with harmony search algorithm is used to provide effective initial forecasts. The heuristic fine-tuning process is then used to generate more accurate forecasts based on the initial forecasts. Extensive experiments based on real fashion retail data were conducted to evaluate the performance of the proposed model. The experimental results demonstrate that the performance of the proposed model is much superior to two recently developed neural network models for seasonal product demand forecasting.

Original language	English
Title of host publication	Proceedings of the 5th IASTED International Conference on Computational Intelligence, CI 2010
Pages	1-6
Number of pages	6
Publication status	Published - 1 Dec 2010
Event	5th IASTED International Conference on Computational Intelligence, CI 2010 - Maui, HI, United States Duration: 23 Aug 2010 → 25 Aug 2010

Conference

Conference	5th IASTED International Conference on Computational Intelligence, CI 2010
Country/Territory	United States
City	Maui, HI
Period	23/08/10 → 25/08/10

Keywords

Extreme learning machine
Harmony search
Neural network
Seasonal product demand forecasting

ASJC Scopus subject areas

Artificial Intelligence
Computational Theory and Mathematics

Cite this

@inproceedings{16c438aa4171474ab63fde8b95c2299d,

title = "An intelligent model for predicting demand pattern",

abstract = "To handle the seasonal product demand forecasting problem, this paper develops an intelligent forecasting model integrating a harmony search algorithm, an extreme learning machine (ELM) and a heuristic finetuning process. The ELM combined with harmony search algorithm is used to provide effective initial forecasts. The heuristic fine-tuning process is then used to generate more accurate forecasts based on the initial forecasts. Extensive experiments based on real fashion retail data were conducted to evaluate the performance of the proposed model. The experimental results demonstrate that the performance of the proposed model is much superior to two recently developed neural network models for seasonal product demand forecasting.",

keywords = "Extreme learning machine, Harmony search, Neural network, Seasonal product demand forecasting",

author = "Wong, {Wai Keung} and Guo, {Z. X.}",

year = "2010",

month = dec,

day = "1",

language = "English",

isbn = "9780889868694",

pages = "1--6",

booktitle = "Proceedings of the 5th IASTED International Conference on Computational Intelligence, CI 2010",

note = "5th IASTED International Conference on Computational Intelligence, CI 2010 ; Conference date: 23-08-2010 Through 25-08-2010",

}

TY - GEN

T1 - An intelligent model for predicting demand pattern

AU - Wong, Wai Keung

AU - Guo, Z. X.

PY - 2010/12/1

Y1 - 2010/12/1

N2 - To handle the seasonal product demand forecasting problem, this paper develops an intelligent forecasting model integrating a harmony search algorithm, an extreme learning machine (ELM) and a heuristic finetuning process. The ELM combined with harmony search algorithm is used to provide effective initial forecasts. The heuristic fine-tuning process is then used to generate more accurate forecasts based on the initial forecasts. Extensive experiments based on real fashion retail data were conducted to evaluate the performance of the proposed model. The experimental results demonstrate that the performance of the proposed model is much superior to two recently developed neural network models for seasonal product demand forecasting.

AB - To handle the seasonal product demand forecasting problem, this paper develops an intelligent forecasting model integrating a harmony search algorithm, an extreme learning machine (ELM) and a heuristic finetuning process. The ELM combined with harmony search algorithm is used to provide effective initial forecasts. The heuristic fine-tuning process is then used to generate more accurate forecasts based on the initial forecasts. Extensive experiments based on real fashion retail data were conducted to evaluate the performance of the proposed model. The experimental results demonstrate that the performance of the proposed model is much superior to two recently developed neural network models for seasonal product demand forecasting.

KW - Extreme learning machine

KW - Harmony search

KW - Neural network

KW - Seasonal product demand forecasting

UR - http://www.scopus.com/inward/record.url?scp=84862091592&partnerID=8YFLogxK

M3 - Conference article published in proceeding or book

SN - 9780889868694

SP - 1

EP - 6

BT - Proceedings of the 5th IASTED International Conference on Computational Intelligence, CI 2010

T2 - 5th IASTED International Conference on Computational Intelligence, CI 2010

Y2 - 23 August 2010 through 25 August 2010

ER -

An intelligent model for predicting demand pattern

Abstract

Conference

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this