Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!howland.reston.ans.net!Germany.EU.net!EU.net!uknet!festival!leeds.ac.uk!news
From: tramcmdc@leeds.ac.uk (M.C.M. DE CARVALHO)
Subject: Neural networks to forecast demand
Keywords: logit model, forecast market share, transport
Message-ID: <tramcmdc.6.000A83F9@leeds.ac.uk>
Organization: University of Leeds
Date: Mon, 20 Feb 1995 10:30:30 +0000 (GMT)
X-Newsreader: Trumpet for Windows [Version 1.0 Rev A]
Lines: 21

I am intending to use neural networks to forecast market share in transports. 
The desaggregate survey with stated preference data has already input in a 
backpropagation neural network and I have got some results, but I do not know 
how to analyse them to get my target,i.e, the network was trained using 
percent of people who choose the alternative input as a desired output.

I would like to get some help in:

How could I get elasticities from neural network results?
How could I use the neural network results to get probabilities like in logit 
model?

Does anyone think that problem (forecast market share) can be solved by neural 
networks? what type of network? 

If anyone knows how to help me, please send messages to my e-mail address:
mclecide@its-sever.novell.leeds.ac.uk

Thanks.

cleci.
