BUS3650

Business applications of neural networks

K Smith
6 points - One 2 hour lecture and one 1-hour tutorial per week - First semester - Clayton

Objectives At the completion of this subject, students should be able to appreciate the advantages and limitations of neural network models for solving a wide range of practical business problems; understand the neural network architectures which are suitable for different types of applications; understand the issues of convergence and training of neural networks; train their own neural networks using commercial software; take a business problem, decide on an architecture, choose training parameters, train the network, test the network and interpret the neural network results.

Synopsis Neural networks have been receiving increasing attention from business and industry over recent years. This course will provide students with the skills necessary to solve practical business problems using commercially available neural network software. The focus of the course will be on the business application, with suitable neural network architectures and convergence issues discussed with reference to each particular application. Students will gain hands-on experience with commercial neural network software packages, and will solve real business problems in tutorials and assignments. Topics to be covered include principles and mechanisms in neural networks; Perceptrons for marketing, and business data classification/analysis; multilayer feedforward neural networks for time series and stock market prediction, and written character recognition; recurrent neural networks for operations/project management, and managerial decision making; convergence issues of neural networks, data mining methodologies, and artificial intelligence in business.

Assessment Examination (2 hours): 50% - Practical work (assignments): 30% - Mid-semester test: 20% - Students must pass the examination in order to pass the subject

Recommended texts

Beale R and Jackson T Neural computing: An introduction IOP Publishing Ltd, 1990

Back to the 1999 Information Technology Handbooks