Enhancing a production rule engine with predictive models using PMML

Davide Sottara, P. Mello, C. Sartori, E. Fry

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

In this paper we describe how the Predictive Model Markup Language (PMML) standard enhances the JBoss Drools production rule engine with native support for using predictive models in business rules. The historic debate between symbolic and connectionist approaches to rule/model orchestration provides numerous examples of hybrid systems combining "hard" and "soft" computing techniques to achieve di-erent levels of integration. Rules are often used to decide when and which model to invoke; model outputs, in turn, can be used to evaluate the preconditions of a rule. In a loosely coupled system, the rule engine calls an external component implementing the predictive model, but this has several disadvantages, most notably the need to setup proper communications and reconcile any di-erence in the way the components encode the data. We propose instead, a tightly integrated system where predictive models and rules become part of the same reasoning framework. The models, encoded using the PMML 4 standard, are loaded and processed by a compiler implemented using the rule engine it-self. The PMML document is transformed into a set of facts that de-ne the model, and a series of rules that formalize the model's behavior. In addition, most PMML data processing, validation, and transformation procedures are also implemented using auto-generated rules. Finally, in oder to integrate model inputs and outputs seamlessly in the inference process, we exploit an extension of the Drools engine which adds native support for uncertainty and/or fuzziness.

Original languageEnglish (US)
Title of host publicationProceedings of the PMML Workshop 2011 - Held in Conjunction with the KDD-2011 Conference
Pages39-47
Number of pages9
DOIs
StatePublished - Sep 26 2011
Externally publishedYes
Event2011 Workshop on Predictive Model Mark-up Language, PMML'11 - Held in Conjunction with the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD-2011 - San Diego, CA, United States
Duration: Aug 21 2011Aug 21 2011

Other

Other2011 Workshop on Predictive Model Mark-up Language, PMML'11 - Held in Conjunction with the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD-2011
CountryUnited States
CitySan Diego, CA
Period8/21/118/21/11

Fingerprint

Markup languages
Engines
Soft computing
Hybrid systems

Keywords

  • PMML
  • Predictive models
  • Rule-based systems

ASJC Scopus subject areas

  • Software
  • Information Systems

Cite this

Sottara, D., Mello, P., Sartori, C., & Fry, E. (2011). Enhancing a production rule engine with predictive models using PMML. In Proceedings of the PMML Workshop 2011 - Held in Conjunction with the KDD-2011 Conference (pp. 39-47) https://doi.org/10.1145/2023598.2023604

Enhancing a production rule engine with predictive models using PMML. / Sottara, Davide; Mello, P.; Sartori, C.; Fry, E.

Proceedings of the PMML Workshop 2011 - Held in Conjunction with the KDD-2011 Conference. 2011. p. 39-47.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sottara, D, Mello, P, Sartori, C & Fry, E 2011, Enhancing a production rule engine with predictive models using PMML. in Proceedings of the PMML Workshop 2011 - Held in Conjunction with the KDD-2011 Conference. pp. 39-47, 2011 Workshop on Predictive Model Mark-up Language, PMML'11 - Held in Conjunction with the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD-2011, San Diego, CA, United States, 8/21/11. https://doi.org/10.1145/2023598.2023604
Sottara D, Mello P, Sartori C, Fry E. Enhancing a production rule engine with predictive models using PMML. In Proceedings of the PMML Workshop 2011 - Held in Conjunction with the KDD-2011 Conference. 2011. p. 39-47 https://doi.org/10.1145/2023598.2023604
Sottara, Davide ; Mello, P. ; Sartori, C. ; Fry, E. / Enhancing a production rule engine with predictive models using PMML. Proceedings of the PMML Workshop 2011 - Held in Conjunction with the KDD-2011 Conference. 2011. pp. 39-47
@inproceedings{d309659b45ef4cb0b9c573736cd86eaa,
title = "Enhancing a production rule engine with predictive models using PMML",
abstract = "In this paper we describe how the Predictive Model Markup Language (PMML) standard enhances the JBoss Drools production rule engine with native support for using predictive models in business rules. The historic debate between symbolic and connectionist approaches to rule/model orchestration provides numerous examples of hybrid systems combining {"}hard{"} and {"}soft{"} computing techniques to achieve di-erent levels of integration. Rules are often used to decide when and which model to invoke; model outputs, in turn, can be used to evaluate the preconditions of a rule. In a loosely coupled system, the rule engine calls an external component implementing the predictive model, but this has several disadvantages, most notably the need to setup proper communications and reconcile any di-erence in the way the components encode the data. We propose instead, a tightly integrated system where predictive models and rules become part of the same reasoning framework. The models, encoded using the PMML 4 standard, are loaded and processed by a compiler implemented using the rule engine it-self. The PMML document is transformed into a set of facts that de-ne the model, and a series of rules that formalize the model's behavior. In addition, most PMML data processing, validation, and transformation procedures are also implemented using auto-generated rules. Finally, in oder to integrate model inputs and outputs seamlessly in the inference process, we exploit an extension of the Drools engine which adds native support for uncertainty and/or fuzziness.",
keywords = "PMML, Predictive models, Rule-based systems",
author = "Davide Sottara and P. Mello and C. Sartori and E. Fry",
year = "2011",
month = "9",
day = "26",
doi = "10.1145/2023598.2023604",
language = "English (US)",
isbn = "9781450308373",
pages = "39--47",
booktitle = "Proceedings of the PMML Workshop 2011 - Held in Conjunction with the KDD-2011 Conference",

}

TY - GEN

T1 - Enhancing a production rule engine with predictive models using PMML

AU - Sottara, Davide

AU - Mello, P.

AU - Sartori, C.

AU - Fry, E.

PY - 2011/9/26

Y1 - 2011/9/26

N2 - In this paper we describe how the Predictive Model Markup Language (PMML) standard enhances the JBoss Drools production rule engine with native support for using predictive models in business rules. The historic debate between symbolic and connectionist approaches to rule/model orchestration provides numerous examples of hybrid systems combining "hard" and "soft" computing techniques to achieve di-erent levels of integration. Rules are often used to decide when and which model to invoke; model outputs, in turn, can be used to evaluate the preconditions of a rule. In a loosely coupled system, the rule engine calls an external component implementing the predictive model, but this has several disadvantages, most notably the need to setup proper communications and reconcile any di-erence in the way the components encode the data. We propose instead, a tightly integrated system where predictive models and rules become part of the same reasoning framework. The models, encoded using the PMML 4 standard, are loaded and processed by a compiler implemented using the rule engine it-self. The PMML document is transformed into a set of facts that de-ne the model, and a series of rules that formalize the model's behavior. In addition, most PMML data processing, validation, and transformation procedures are also implemented using auto-generated rules. Finally, in oder to integrate model inputs and outputs seamlessly in the inference process, we exploit an extension of the Drools engine which adds native support for uncertainty and/or fuzziness.

AB - In this paper we describe how the Predictive Model Markup Language (PMML) standard enhances the JBoss Drools production rule engine with native support for using predictive models in business rules. The historic debate between symbolic and connectionist approaches to rule/model orchestration provides numerous examples of hybrid systems combining "hard" and "soft" computing techniques to achieve di-erent levels of integration. Rules are often used to decide when and which model to invoke; model outputs, in turn, can be used to evaluate the preconditions of a rule. In a loosely coupled system, the rule engine calls an external component implementing the predictive model, but this has several disadvantages, most notably the need to setup proper communications and reconcile any di-erence in the way the components encode the data. We propose instead, a tightly integrated system where predictive models and rules become part of the same reasoning framework. The models, encoded using the PMML 4 standard, are loaded and processed by a compiler implemented using the rule engine it-self. The PMML document is transformed into a set of facts that de-ne the model, and a series of rules that formalize the model's behavior. In addition, most PMML data processing, validation, and transformation procedures are also implemented using auto-generated rules. Finally, in oder to integrate model inputs and outputs seamlessly in the inference process, we exploit an extension of the Drools engine which adds native support for uncertainty and/or fuzziness.

KW - PMML

KW - Predictive models

KW - Rule-based systems

UR - http://www.scopus.com/inward/record.url?scp=80053049517&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80053049517&partnerID=8YFLogxK

U2 - 10.1145/2023598.2023604

DO - 10.1145/2023598.2023604

M3 - Conference contribution

AN - SCOPUS:80053049517

SN - 9781450308373

SP - 39

EP - 47

BT - Proceedings of the PMML Workshop 2011 - Held in Conjunction with the KDD-2011 Conference

ER -