webmaster: Sven F. Crone
Centre for Forecasting
Lancaster LA1 4YF
eMail sven dot crone (at)
neural-forecasting dot com
& Branch Summary
On these pages you will find
information & links on individual researchers, research groups and
associations with a track record in neural forecasting. Wish to add something
to this portal ? Link exchange only in NN & forecasting sites! Send
info, links etc. to
A variety of resources exist, publishing information on the application of
NN in forecasting. However, very few books are dedicated to this topic,
focussing either on the technical specification of neural networks as a method,
or the forecasting domain.
On the following pages please find some references to the
most recommended publications to build the necessary skills for forecasting with
artificial neural networks. They incorporate general introductions to Neural
Networks or Forecasting as well as specific Literature on Forecasting with NN,
although there are very few dedicated publications to date. In any way, if you
want to learn about NN in forecasting, you need to essentially understand both:
Neural Network design, training and evaluation as well as forecasting domain.
How to Start reading into the
field ... (a personal view)
If you don't have time to indulge on
reading - you are doing something very wrong - but here is the shortest way in.
And NO there is no way around it.
1. Read introduction papers
Zhang, G., B. Eddy Patuwo, et al. (1998). "Forecasting
with artificial neural networks: The state of the art." International Journal of
Forecasting 14(1): 35-62.
Abstract: Interest in using artificial neural networks (ANNs)
for forecasting has led to a tremendous surge in research activities in the past
decade. While ANNs provide a great deal of promise, they also embody much
uncertainty. Researchers to date are still not certain about the effect of key
factors on forecasting performance of ANNs. This paper presents a
state-of-the-art survey of ANN applications in forecasting. Our purpose is to
provide (1) a synthesis of published research in this area, (2) insights on ANN
modelling issues, and (3) the future research directions.
In 06/2004 it was still free for download
at the top 10 requested papers at Elsevier
Unfortunately, you will already need to understand neural
networks to appreciate it fully. So now get to know NN and forecasting. This is your
2. Read relevant BOOKS
Neural Smithing: Supervised Learning in
Feedforward Artificial Neural Networks
Russell D. Reed,
Robert J. Marks II
Most books on the field give a very objective approach
to connectionism, and describe mathematical knowledge
for getting Neural Networks to train. This work of art
approaches the problem from a practical point of view,
discussing issues that anyone would be faced with when
working with Neural Networks.
Things like setting learning rates, using stochastic
approximation, adding momentum and deciding training
times are all key factors that are discussed in depth.
The visual aids are extremely helpful, and allow the
reader to develop a fell and intuition for Neural
A definite must for neural optimisation fanatics!
3. Reread Papers noted under 1!
4. Read FQ from Neural Networks Newsgroup