Högskolan i Skövde

his.sePublikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • apa-cv
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Understanding expert behavior in adjusting models: Expert behaviour simulation
Högskolan i Skövde, Institutionen för informationsteknologi.
2021 (engelsk)Independent thesis Advanced level (degree of Master (One Year)), 10 poäng / 15 hpOppgave
Abstract [en]

Most companies nowadays employ experts who work in tandem with a numerical forecasting system to improve the latter’s accuracy. Studies have shown that in many cases these forecasts actually improve the final forecast, hence the popularity of the experts. Many other researchers tried to understand the behaviour of experts when it comes to the adjustments made and found that they are mostly optimistic and predictable to a high degree with a tendency to adhering to familiar habits. In this project, an AI based solution was built in contrast to the mathematical approach followed by Franses et al [1] to prove the uniformity expert’s decisions. Endorsing the work of Franses et al, the AI model was able to simulate the adjustments made by the expert to a satisfactory degree without great computational overhead as well as proving that the corrections that the expert is making is systematic. Moreover, we discussed the areas at which the model can be used to aidexperts in their day to day work which could save them time as well as the ethical barriers which could end up harming the expert, the business or both. Finally, limitation of solutions and suggestions to fix them were discussed which lays the ground for future work in this area.

sted, utgiver, år, opplag, sider
2021. , s. 47
HSV kategori
Identifikatorer
URN: urn:nbn:se:his:diva-20826OAI: oai:DiVA.org:his-20826DiVA, id: diva2:1623686
Eksternt samarbeid
Skövde AI Lab (SAIL)
Fag / kurs
Informationsteknologi
Utdanningsprogram
Data Science - Master’s Programme
Veileder
Examiner
Tilgjengelig fra: 2021-12-30 Laget: 2021-12-30 Sist oppdatert: 2021-12-30bibliografisk kontrollert

Open Access i DiVA

fulltext(4318 kB)182 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 4318 kBChecksum SHA-512
064b16f502768cec5205312e7682a97268cf6a823666058ef534e6d234dffe0ee300a5318e54a104ffea25b324e8e14f1f3469421099645bdf6fa88a9779a6fc
Type fulltextMimetype application/pdf

Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 182 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

urn-nbn

Altmetric

urn-nbn
Totalt: 154 treff
RefereraExporteraLink to record
Permanent link

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