Driftstörningar
Det förekommer återkommande driftstörningar på några av sök-portalerna på grund av hög belastning. Vi arbetar på att lösa problemet, ni kan tillfälligt mötas av ett felmeddelande.
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Understanding human generated decision data
Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för programvaruteknik.ORCID-id: 0000-0003-0396-1993
2020 (Engelska)Ingår i: Lecture Notes in Business Information Processing / [ed] Shishkov B., Springer, 2020, Vol. 391, s. 362-374Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

In order to design intent-driven systems, the understanding of how the data is generated is essential. Without the understanding of the data generation process, it is not possible to use interventions, and counterfactuals. Interventions, and counterfactuals, are useful tools in order to achieve an artificial intelligence which can improve the system itself. We will create an understanding, and a model, of how data about decisions are generated, as well as used, by human decision makers. The research data were collected with the help of focus group interviews, and questionnaires. The models were built and evaluated with the help of, bayesian statistics, probability programming, and discussions with the practitioners. When we are combining, probabilistic programming models, extended machine learning algorithms, and data science processes, into a directed acyclic graph, we can mimic the process of human generated decision data. We believe the usage of a directed acyclic graph, to combine the functions and models, is a good base for mimic human generated decision data. Our next step is to evaluate if flow-based programming can be used as a framework for realization of components, useful in intent-driven systems. © Springer Nature Switzerland AG 2020.

Ort, förlag, år, upplaga, sidor
Springer, 2020. Vol. 391, s. 362-374
Serie
Lecture Notes in Business Information Processing, ISSN 1865-1348, E-ISSN 1865-1356
Nyckelord [en]
Bayesian statistics, Human decisions, Probabilistic programming, Data Science, Decision making, Directed graphs, Graph algorithms, Learning algorithms, Machine learning, Surveys, Counterfactuals, Data generation, Design intent, Directed acyclic graph (DAG), Research data, Software design
Nationell ämneskategori
Datavetenskap (datalogi) Sannolikhetsteori och statistik
Identifikatorer
URN: urn:nbn:se:bth-20292DOI: 10.1007/978-3-030-52306-0_26ISI: 000759772900026Scopus ID: 2-s2.0-85088529923ISBN: 9783030523053 (tryckt)OAI: oai:DiVA.org:bth-20292DiVA, id: diva2:1458235
Konferens
10th International Symposium on Business Modeling and Software Design, BMSD 2020; Berlin; Germany; 6 July 2020 through 8 July 2020
Tillgänglig från: 2020-08-14 Skapad: 2020-08-14 Senast uppdaterad: 2025-09-30Bibliografiskt granskad
Ingår i avhandling
1. Towards Intent-Driven Systems Based on Context Frames
Öppna denna publikation i ny flik eller fönster >>Towards Intent-Driven Systems Based on Context Frames
2021 (Engelska)Doktorsavhandling, sammanläggning (Övrigt vetenskapligt)
Abstract [en]

In this research project we investigate how machine actors can support the business intents (desired outcomes) of an enterprise via predictive execution flows, prescriptive execution flows, and bidirectional knowledge creation between human actors and machine actors. A context frame supports bidirectional knowledge creation via interventions and counterfactual analysis. An intent-driven system combines execution flows to obtain business intents, and a context frame is a component in these flows. 

Our aim is to develop theoretical frameworks supporting intent-driven systems and context frames, and to validate the components needed to realize such frame- works. 

We are using the design science framework as our research framework. During our design science study we have used the following research methods: systematic literature review, case study, quasi experiment, action research, and evaluation research. 

We have created theoretical frameworks supporting intent-driven systems, and context frames, and implemented needed functionality in the involved components. The framework supports knowledge creation and knowledge validation. The possibility of using the knowledge for predictive analysis, prescriptive analysis, and counterfactual analysis, makes it possible to obtain bidirectional knowledge creation between a human actor and a machine actor. This enables a context frame to be part of an intent-driven system which supports predictive, and prescriptive, executions flows. 

The produced artifacts provide answers to our research questions. These answers are a base for theoretical frameworks supporting intent-driven systems and context frames, and provide knowledge of how to construct the components needed to realize these frameworks. 

Ort, förlag, år, upplaga, sidor
Karlskrona: Blekinge Tekniska Högskola, 2021. s. 50
Serie
Blekinge Institute of Technology Doctoral Dissertation Series, ISSN 1653-2090 ; 2021:08
Nyckelord
business intent, knowledge creation, decision making, rule adherence, OODA-loop, causal models
Nationell ämneskategori
Programvaruteknik
Forskningsämne
Programvaruteknik
Identifikatorer
urn:nbn:se:bth-22178 (URN)978-91-7295-430-4 (ISBN)
Disputation
2021-12-10, J1630 + Zoom, Campus Gräsvik, Karlskrona, 09:30 (Engelska)
Opponent
Handledare
Forskningsfinansiär
KK-stiftelsen
Tillgänglig från: 2021-10-08 Skapad: 2021-10-07 Senast uppdaterad: 2025-09-30Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltextScopus

Person

Silvander, Johan

Sök vidare i DiVA

Av författaren/redaktören
Silvander, Johan
Av organisationen
Institutionen för programvaruteknik
Datavetenskap (datalogi)Sannolikhetsteori och statistik

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetricpoäng

doi
isbn
urn-nbn
Totalt: 326 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf