|
Title:
|
E-COMMERCE: FORECASTING DEMAND FOR NEWPRODUCTS |
|
Author(s):
|
Manuel Carlos B. Figueiredo |
|
ISBN:
|
978-972-8924-66-9 |
|
Editors:
|
Piet Kommers, Pedro Isaías and Nian-Shing Chen |
|
Year:
|
2008 |
|
Edition:
|
Single |
|
Keywords:
|
E-Commerce, Forecasting Demand, Neural Networks, Combining Forecasts |
|
Type:
|
Full Paper |
|
First Page:
|
102 |
|
Last Page:
|
112 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
When a new product is offered in the website of a company it will be suddenly available to thousands or even millions of
potential buyers and essentially we do not know or control who we make the offer to. In addition, there will be no
historical demand data to analyse. This absence of past sales data, changes in fashion and product design causes
difficulties in forecasting demand accurately. A new approach to demand forecasting using neural networks is presented
and the main questions concerning the implementation of neural network models are discussed. The models developed
are tested using data for one particular company, and the results are compared with those obtained from traditional profile
forecasting methods. The potentialities of combining the forecasts obtained from these two different approaches are
explored. |
|
|
|
|
|
|
