Minimum message length criterion for second-order polynomial model discovery

Grace W Rumantir

doi:10.1007/3-540-45571-X_7

Minimum message length criterion for second-order polynomial model discovery

Grace W Rumantir

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

3 Citations (Scopus)

Abstract

This paper proposes a method based on the Minimum Message Length (MML) Principle for the task of discovering polynomial models up to the second order. The method is compared with a number of other selection criteria in the ability to, in an automated manner, discover a model given the generated data. Of particular interest is the ability of the methods to discover (1) second-order independent variables, (2) independent variables with weak causal relationships with the target variable given a small sample size, and (3) independent variables with weak links to the target variable but strong links from other variables which are not directly linked with the target variable. A common non-backtracking search strategy has been developed and is used with all of the model selection criteria.

Original language	English
Title of host publication	Knowledge Discovery and Data Mining - Current Issues and New Applications
Subtitle of host publication	4th Pacific-Asia Conference, PAKDD 2000 Kyoto, Japan, April 18-20, 2000 Proceedings
Editors	Takao Terano, Huan Liu, Arbee L.P. Chen
Place of Publication	Berlin Germany
Publisher	Springer
Pages	40-48
Number of pages	9
ISBN (Print)	3540673822
DOIs	https://doi.org/10.1007/3-540-45571-X_7
Publication status	Published - 2000
Event	Pacific-Asia Conference on Knowledge Discovery and Data Mining 2000 - Kyoto, Japan Duration: 18 Apr 2000 → 20 Apr 2000 Conference number: 4th https://link.springer.com/book/10.1007/3-540-45571-X (Proceedings)

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
ISSN (Print)	0302-9743

Conference

Conference	Pacific-Asia Conference on Knowledge Discovery and Data Mining 2000
Abbreviated title	PAKDD 2000
Country/Territory	Japan
City	Kyoto
Period	18/04/00 → 20/04/00
Internet address	https://link.springer.com/book/10.1007/3-540-45571-X (Proceedings)

Access to Document

10.1007/3-540-45571-X_7

Cite this

Rumantir, G. W. (2000). Minimum message length criterion for second-order polynomial model discovery. In T. Terano, H. Liu, & A. L. P. Chen (Eds.), Knowledge Discovery and Data Mining - Current Issues and New Applications : 4th Pacific-Asia Conference, PAKDD 2000 Kyoto, Japan, April 18-20, 2000 Proceedings (pp. 40-48). (Lecture Notes in Computer Science). Springer. https://doi.org/10.1007/3-540-45571-X_7

Rumantir, Grace W. / Minimum message length criterion for second-order polynomial model discovery. Knowledge Discovery and Data Mining - Current Issues and New Applications : 4th Pacific-Asia Conference, PAKDD 2000 Kyoto, Japan, April 18-20, 2000 Proceedings . editor / Takao Terano ; Huan Liu ; Arbee L.P. Chen. Berlin Germany : Springer, 2000. pp. 40-48 (Lecture Notes in Computer Science).

@inproceedings{a42b974ecc764ccdac54d265db7c6d3f,

title = "Minimum message length criterion for second-order polynomial model discovery",

abstract = "This paper proposes a method based on the Minimum Message Length (MML) Principle for the task of discovering polynomial models up to the second order. The method is compared with a number of other selection criteria in the ability to, in an automated manner, discover a model given the generated data. Of particular interest is the ability of the methods to discover (1) second-order independent variables, (2) independent variables with weak causal relationships with the target variable given a small sample size, and (3) independent variables with weak links to the target variable but strong links from other variables which are not directly linked with the target variable. A common non-backtracking search strategy has been developed and is used with all of the model selection criteria.",

author = "Rumantir, \{Grace W\}",

year = "2000",

doi = "10.1007/3-540-45571-X\_7",

language = "English",

isbn = "3540673822",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "40--48",

editor = "Takao Terano and Huan Liu and Chen, \{Arbee L.P.\}",

booktitle = "Knowledge Discovery and Data Mining - Current Issues and New Applications",

address = "Switzerland",

note = "Pacific-Asia Conference on Knowledge Discovery and Data Mining 2000, PAKDD 2000 ; Conference date: 18-04-2000 Through 20-04-2000",

url = "https://link.springer.com/book/10.1007/3-540-45571-X",

}

Rumantir, GW 2000, Minimum message length criterion for second-order polynomial model discovery. in T Terano, H Liu & ALP Chen (eds), Knowledge Discovery and Data Mining - Current Issues and New Applications : 4th Pacific-Asia Conference, PAKDD 2000 Kyoto, Japan, April 18-20, 2000 Proceedings . Lecture Notes in Computer Science, Springer, Berlin Germany, pp. 40-48, Pacific-Asia Conference on Knowledge Discovery and Data Mining 2000, Kyoto, Japan, 18/04/00. https://doi.org/10.1007/3-540-45571-X_7

Minimum message length criterion for second-order polynomial model discovery. / Rumantir, Grace W.
Knowledge Discovery and Data Mining - Current Issues and New Applications : 4th Pacific-Asia Conference, PAKDD 2000 Kyoto, Japan, April 18-20, 2000 Proceedings . ed. / Takao Terano; Huan Liu; Arbee L.P. Chen. Berlin Germany: Springer, 2000. p. 40-48 (Lecture Notes in Computer Science).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Minimum message length criterion for second-order polynomial model discovery

AU - Rumantir, Grace W

N1 - Conference code: 4th

PY - 2000

Y1 - 2000

N2 - This paper proposes a method based on the Minimum Message Length (MML) Principle for the task of discovering polynomial models up to the second order. The method is compared with a number of other selection criteria in the ability to, in an automated manner, discover a model given the generated data. Of particular interest is the ability of the methods to discover (1) second-order independent variables, (2) independent variables with weak causal relationships with the target variable given a small sample size, and (3) independent variables with weak links to the target variable but strong links from other variables which are not directly linked with the target variable. A common non-backtracking search strategy has been developed and is used with all of the model selection criteria.

AB - This paper proposes a method based on the Minimum Message Length (MML) Principle for the task of discovering polynomial models up to the second order. The method is compared with a number of other selection criteria in the ability to, in an automated manner, discover a model given the generated data. Of particular interest is the ability of the methods to discover (1) second-order independent variables, (2) independent variables with weak causal relationships with the target variable given a small sample size, and (3) independent variables with weak links to the target variable but strong links from other variables which are not directly linked with the target variable. A common non-backtracking search strategy has been developed and is used with all of the model selection criteria.

U2 - 10.1007/3-540-45571-X_7

DO - 10.1007/3-540-45571-X_7

M3 - Conference Paper

SN - 3540673822

T3 - Lecture Notes in Computer Science

SP - 40

EP - 48

BT - Knowledge Discovery and Data Mining - Current Issues and New Applications

A2 - Terano, Takao

A2 - Liu, Huan

A2 - Chen, Arbee L.P.

PB - Springer

CY - Berlin Germany

T2 - Pacific-Asia Conference on Knowledge Discovery and Data Mining 2000

Y2 - 18 April 2000 through 20 April 2000

ER -

Rumantir GW. Minimum message length criterion for second-order polynomial model discovery. In Terano T, Liu H, Chen ALP, editors, Knowledge Discovery and Data Mining - Current Issues and New Applications : 4th Pacific-Asia Conference, PAKDD 2000 Kyoto, Japan, April 18-20, 2000 Proceedings . Berlin Germany: Springer. 2000. p. 40-48. (Lecture Notes in Computer Science). doi: 10.1007/3-540-45571-X_7