Abstract
This paper demonstrates a mechanism whereby rules can be extracted from a feedforward neural network trained to characterize the inflation "pass-through" problem in American monetary policy, defined as the relationship between changes in the growth rate(s) of individual commodities and the economy-wide rate of growth of consumer prices. Monthly price data are encoded and used to train a group of candidate connectionist architectures. One candidate is selected for rule extraction, using a custom decompositional extraction algorithm that generates rules in human-readable and machine-executable form. Rule and network accuracy are compared, and comments are made on the relationships expressed within the discovered rules. The types of discovered relationships could be used to guide monetary policy decisions.
Original language | English |
---|---|
Title of host publication | Proceedings of the 2010 International Conference on Artificial Intelligence, ICAI 2010 |
Editors | Hamid R. Arabnia, David de la Fuente, Elena B. Kozerenko, et al |
Publisher | CSREA |
Pages | 318-324 |
Number of pages | 7 |
ISBN (Print) | 978-1-6013-2148-0 |
Publication status | Published - 1 Dec 2010 |
Event | 2010 International Conference on Artificial Intelligence - Las Vegas, NV, United States Duration: 12 Jul 2010 → 15 Jul 2010 |
Conference
Conference | 2010 International Conference on Artificial Intelligence |
---|---|
Abbreviated title | IC-AI 2010 |
Country/Territory | United States |
City | Las Vegas, NV |
Period | 12/07/10 → 15/07/10 |
Keywords
- consumer prices
- data mining
- inflation
- neural network
- rule generation