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
A comparison of LightGBM and perceptron for classifying the cause of salary differences between workgroups: Comparative study for classifying the reason for salary difference with different machine learning algorithms
Högskolan i Skövde, Institutionen för informationsteknologi.
2021 (engelsk)Independent thesis Basic level (degree of Bachelor), 20 poäng / 30 hpOppgave
Abstract [en]

Machine learning is part of what is called AI. It is defined as the application of an algorithm to improve a result through learning.

In Sweden, the law requires large companies and organizations to revise their salaries every year to ensure there is no wage disparity between men and women. This could be used as an assisting tool if machine learning is applied to the analysis process.

By training two different models and test them against the same test dataset different metrics can be obtained and analyzed to see how they perform in comparison to each other. The results show a slightly improved performance by the perceptron and that there is room for further development.

This study is limited to a smaller dataset for training and testing. But in the future, more relevant features and larger datasets could be added for training the models and lead to a more accurate model.

sted, utgiver, år, opplag, sider
2021. , s. 38
HSV kategori
Identifikatorer
URN: urn:nbn:se:his:diva-20195OAI: oai:DiVA.org:his-20195DiVA, id: diva2:1577628
Eksternt samarbeid
SysArb AB
Fag / kurs
Informationsteknologi
Utdanningsprogram
Computer Science - Specialization in Systems Development
Veileder
Examiner
Tilgjengelig fra: 2021-07-02 Laget: 2021-07-02 Sist oppdatert: 2021-07-02bibliografisk kontrollert

Open Access i DiVA

fulltext(883 kB)247 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 883 kBChecksum SHA-512
73cefe340ae7c983d86c50fc832368a6eda508d9b1dbb767520450272d9faa89cbfaad4e2784d4266238ee721f31936e027bfe6794331014631bb01f7ca5eed1
Type fulltextMimetype application/pdf

Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 247 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: 70 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