Improving Data Science Projects by Enriching Analytical Models with Domain Knowledge

Research output: Chapter in Book/Entry/PoemConference contribution

5 Scopus citations

Abstract

Domain knowledge is very important to support the development of analytic models. However, in today's data science projects, domain knowledge is typically documented, but not captured and integrated with the actual analytic model. This raises problems in interoperability and traceability of the relevant domain knowledge that is used to develop an analytic model. To address this challenge, this paper proposes a Knowledge Enriched Analytic Model (KEAM) to enrich analytic models with domain knowledge. To explore the proposed methodology and its benefits, a case study explores the utilization of KEAM to support the development of a Bayesian Network model within the smart manufacturing domain. The case study shows that the efficiency in developing an analytic model is improved by using the proposed KEAM.

Original languageEnglish (US)
Title of host publicationProceedings - 2018 IEEE International Conference on Big Data, Big Data 2018
EditorsNaoki Abe, Huan Liu, Calton Pu, Xiaohua Hu, Nesreen Ahmed, Mu Qiao, Yang Song, Donald Kossmann, Bing Liu, Kisung Lee, Jiliang Tang, Jingrui He, Jeffrey Saltz
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2828-2837
Number of pages10
ISBN (Electronic)9781538650356
DOIs
StatePublished - Jul 2 2018
Event2018 IEEE International Conference on Big Data, Big Data 2018 - Seattle, United States
Duration: Dec 10 2018Dec 13 2018

Publication series

NameProceedings - 2018 IEEE International Conference on Big Data, Big Data 2018

Conference

Conference2018 IEEE International Conference on Big Data, Big Data 2018
Country/TerritoryUnited States
CitySeattle
Period12/10/1812/13/18

Keywords

  • analytic model
  • interoperability
  • knowledge
  • smart manufacturing
  • traceability

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems

Fingerprint

Dive into the research topics of 'Improving Data Science Projects by Enriching Analytical Models with Domain Knowledge'. Together they form a unique fingerprint.

Cite this