A connectionist approach to producing rules describing monthly UK Divisia data

Vincent A. Schmidt; Jane M. Binner

A connectionist approach to producing rules describing monthly UK Divisia data

Vincent A. Schmidt, Jane M. Binner

Economics, Finance and Entrepreneurship

Research output: Chapter in Book/Published conference output › Conference publication

Abstract

This paper demonstrates a mechanism, whereby rules can be extracted from a feedforward neural network trained to characterize the money-price relationship, defined as the relationship between the rate of growth of the money supply and inflation. Monthly Divisia component data is 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 2008 International Conference on Artificial Intelligence, ICAI 2008 and Proceedings of the 2008 International Conference on Machine Learning; Models, Technologies and Applications
Pages	468-474
Number of pages	7
Publication status	Published - 1 Dec 2008
Event	2008 International Conference on Artificial Intelligence, ICAI 2008 and 2008 International Conference on Machine Learning; Models, Technologies and Applications, MLMTA 2008 - Las Vegas, NV, United Kingdom Duration: 14 Jul 2008 → 17 Jul 2008

Conference

Conference	2008 International Conference on Artificial Intelligence, ICAI 2008 and 2008 International Conference on Machine Learning; Models, Technologies and Applications, MLMTA 2008
Country/Territory	United Kingdom
City	Las Vegas, NV
Period	14/07/08 → 17/07/08

Keywords

Data mining
Divisia
Inflation
Neural Network
Rule generation

Cite this

@inproceedings{c061e88cc7984f99b5afaa44a62ff947,

title = "A connectionist approach to producing rules describing monthly UK Divisia data",

abstract = "This paper demonstrates a mechanism, whereby rules can be extracted from a feedforward neural network trained to characterize the money-price relationship, defined as the relationship between the rate of growth of the money supply and inflation. Monthly Divisia component data is 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.",

keywords = "Data mining, Divisia, Inflation, Neural Network, Rule generation",

author = "Schmidt, {Vincent A.} and Binner, {Jane M.}",

year = "2008",

month = dec,

day = "1",

language = "English",

isbn = "1601320728",

pages = "468--474",

booktitle = "Proceedings of the 2008 International Conference on Artificial Intelligence, ICAI 2008 and Proceedings of the 2008 International Conference on Machine Learning; Models, Technologies and Applications",

note = "2008 International Conference on Artificial Intelligence, ICAI 2008 and 2008 International Conference on Machine Learning; Models, Technologies and Applications, MLMTA 2008 ; Conference date: 14-07-2008 Through 17-07-2008",

}

Schmidt, VA & Binner, JM 2008, A connectionist approach to producing rules describing monthly UK Divisia data. in Proceedings of the 2008 International Conference on Artificial Intelligence, ICAI 2008 and Proceedings of the 2008 International Conference on Machine Learning; Models, Technologies and Applications. pp. 468-474, 2008 International Conference on Artificial Intelligence, ICAI 2008 and 2008 International Conference on Machine Learning; Models, Technologies and Applications, MLMTA 2008, Las Vegas, NV, United Kingdom, 14/07/08.

A connectionist approach to producing rules describing monthly UK Divisia data. / Schmidt, Vincent A.; Binner, Jane M.
Proceedings of the 2008 International Conference on Artificial Intelligence, ICAI 2008 and Proceedings of the 2008 International Conference on Machine Learning; Models, Technologies and Applications. 2008. p. 468-474.

Research output: Chapter in Book/Published conference output › Conference publication

TY - GEN

T1 - A connectionist approach to producing rules describing monthly UK Divisia data

AU - Schmidt, Vincent A.

AU - Binner, Jane M.

PY - 2008/12/1

Y1 - 2008/12/1

N2 - This paper demonstrates a mechanism, whereby rules can be extracted from a feedforward neural network trained to characterize the money-price relationship, defined as the relationship between the rate of growth of the money supply and inflation. Monthly Divisia component data is 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.

AB - This paper demonstrates a mechanism, whereby rules can be extracted from a feedforward neural network trained to characterize the money-price relationship, defined as the relationship between the rate of growth of the money supply and inflation. Monthly Divisia component data is 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.

KW - Data mining

KW - Divisia

KW - Inflation

KW - Neural Network

KW - Rule generation

UR - http://www.scopus.com/inward/record.url?scp=62749120124&partnerID=8YFLogxK

M3 - Conference publication

AN - SCOPUS:62749120124

SN - 1601320728

SN - 9781601320728

SP - 468

EP - 474

BT - Proceedings of the 2008 International Conference on Artificial Intelligence, ICAI 2008 and Proceedings of the 2008 International Conference on Machine Learning; Models, Technologies and Applications

T2 - 2008 International Conference on Artificial Intelligence, ICAI 2008 and 2008 International Conference on Machine Learning; Models, Technologies and Applications, MLMTA 2008

Y2 - 14 July 2008 through 17 July 2008

ER -

A connectionist approach to producing rules describing monthly UK Divisia data

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this