[ecoop-info] Workshop on Neural Networks for Time Series Prediction, Stellenbosch, South Africa

Forecasting Training s.crone at lancaster.ac.uk
Wed Jun 10 20:09:05 CEST 2009

Call for participation
       1st Hands-on Training Workshop on

     Forecasting & Time Series Predictions
        with Artificial Neural Networks

              17-19 September 2009
 Wallenberg Centre, Institute of Advanced Study
    Stellenbosch University, South Africa

You are invited to participate in a 3-day training workshop on Forecasting and Time Series Prediction with Artificial Neural Networks, to be held in conjunction with the 38th Annual Conference of the Operations Research Society of South Africa (ORSSA'09), Stellenbosch, South Africa (www.orssaconf.co.za). 

Course description: 
Artificial neural networks (NN) have revolutionized the way researchers and practitioners solve complex, real-world problems in business, finance, economics, and engineering. Today, NNs are being routinely used by specialists in a wide range of predictive tasks such as forecasting electrical load, financial data, consumer packaged goods in retail and supply chain management, call volumes in call centres etc. However, their modelling and specification requires expert knowledge often not available in companies. We are pleased to announce the first 3-day NN training workshop on time series prediction and forecasting to be held right here in South Africa. 
Course design:
The course will be 3 full days of maths-lite lectures and hands-on exercises using a free NN software simulator – so bring along your laptop to run experiments! 
Target audience: 
Whether you are a demand planner, engineer, financial analyst, researcher, or student, the course is designed to help you acquire the knowledge, the skills and the competence you need to utilize this cutting-edge technology for solving predictive problems. You will be exposed to the theoretical concepts and hands-on applications of NN that will be invaluable in your day-to-day decision-making processes. The hands-on format will allow you to follow the course even without a sound mathematical or statistical background. Even if you are already familiar with ANN, you will learn tricks-of-the-trade and explore or develop your own. Don’t miss out! Get your organisation ahead of the competition by equipping yourself with this futuristic technique. 
Course Coverage: 
History of neural networks, specifying neural network architectures (number of layers, number of nodes, feedback etc.), Backpropagation and other learning algorithms for neural networks, Applications of neural networks in function approximation, linear and nonlinear time series prediction, and nonlinear system identification, hands-on examples in time series and causal modelling, Fundamentals of time series forecasting, Modelling neural networks for smoothing and regression, Evaluating Neural Network forecasting accuracy, Out-of-Sample Empirical Design of Neural Network Experiments 
Your Lecturer: 
The course will be taught by Dr. Sven F. Crone, Assistant Professor in Management Science at Lancaster University Management School and deputy director of the Lancaster Centre for Forecasting, one of the world’s largest research units dedicated to forecasting. With a PhD in neural forecasting, he frequently speaks at international conferences and runs forecasting competitions. Sven regularly teaches forecasting, both at university, in practitioners courses and in tutorials for IBF and IEEE CIS. He has over 8 years of corporate experience, having consulted with companies incl. retailer Tesco UK, manufacturer of FMCG Beiersdorf GER, Chemicals producer Celanese USA, copper producer Codelco Chile, and insurance AXA Switzerland etc.
Software to be used: 
Intelligent Forecaster offers industry-grade software (made in Germany) developed exclusively and specifically for  time series forecasting with the most up-to-date and advanced methods from Artificial Intelligence: Support Vector Regression (SVR) and artificial Neural Networks (NN). These allow unprecedented accuracy from nonlinear, data-driven and non-parametric prediction. The software provides various expert features (i.e. input-variable & lag-identification, data-preprocessing, ensembles) for multiple forecasting horizons across fixed forecasting horizon, rolling origin evaluation across a set of multiple error measures). [Read more ...] 

The workshop is supported by the NRF under the KISC grant scheme. The idea of hosting the NN workshop in South Africa was conceptualised by Dr. Chipo Mlambo during her time as a lecturer in Business Forecasting at the Universiy of Stellenbosch (USB), and it is here that the funding was initially granted. We are grateful to the NRF and colleagues at USB for their kind support of the workshop.

Costs & Registration
Registration Fee for 3 full days:
ZAR 3000 (ca. €260/$365), before 31 July 2009
ZAR 3900 (ca. €340/$475), after 31 July 2009

The fee includes a NN software simulator on CD for experiments, data, stationery & coffee/tea & lunches. Accommodation is not included - for a list of accommodations please visit the ORSSA conference website (see left) held at the same venue

For any enquiries and reservations please contact Dr. Chipo Mlambo via email: 
Dr Chipo Mlambo
University of Cape Town (UCT)
Graduate School of Business
Tel: +27 (0)21 406 1442
Fax: +27 (0)21 406 1412
chipo.mlambo at gsb.uct.ac.za

More information about the ecoop-info mailing list