Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Artificiell intelligens och maskinlärning i finansbranschen
KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Health Informatics.
KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Health Informatics.
2018 (Swedish)Independent thesis Basic level (university diploma), 10 credits / 15 HE creditsStudent thesisAlternative title
Artificial intelligence and machine learning in the financial industry (English)
Abstract [sv]

För att alltid kunna erbjuda sina tjänster som ett finansiellt institut så är det viktigt att alltid vara informerad och uppdaterad när nya regelverk träder i kraft. Idag bidrar det till höga kostnader då det till stor del sker med humanitär kraft. För att se i vilken mån det går att effektivisera med hjälp av artificiell intelligens eller maskininlärning gjordes en litteraturstudie för att detta. Undersökningen visade att maskininlärning var den bäst lämpade metoden för denna problemställning. Arbetet hade inte de mest optimala förutsättningar för att få så säkert resultat som möjligt, trots detta visade resultatet på god förmåga att kunna klassificera produkter mot regelverk. Möjligheten till att applicera maskininlärning eller artificiell intelligens är god men det är viktigt med extremt stora mängder tränings- och testdata för att kunna effektivisera finansbranschen.

Abstract [en]

To always be able to offer their services as a financial institution, it’s important for them to always stay informed and updated when new regulations come into force. Today it contributes to high costs, largely due to humanitarian power. A literature study was performed to see as to what extent artificial intelligence or machine learning could be used to reduce the problem. The result of the study showed that machine learning was the best suited method for this problem. There were not the most optimal conditions to achieve the best possible result, despite that, the result gave promising ability to classify products to regulations. The possibility of applying machine learning and artificial intelligence is good but it is important to have extremely large amounts of training and test data in order to make the financial industry more effective. 

Place, publisher, year, edition, pages
2018. , p. 46
Series
TRITA-STH ; 2018:1
Keywords [en]
Artificial intelligence, machine learning, compliance, regulations, financial institution, bank
Keywords [sv]
Artificiell intelligens, maskininlärning, compliance, regelverk, finansiellt institut, bank
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:kth:diva-224326OAI: oai:DiVA.org:kth-224326DiVA, id: diva2:1190895
External cooperation
Nordicstation
Educational program
Bachelor of Science in Engineering - Computer Engineering
Supervisors
Examiners
Available from: 2018-06-13 Created: 2018-03-15 Last updated: 2018-06-13Bibliographically approved

Open Access in DiVA

Examensarbete(1514 kB)180 downloads
File information
File name FULLTEXT01.pdfFile size 1514 kBChecksum SHA-512
430c88d97a74bcdc595c9fe026fe1eba2ed73268492b518c77b783fdf652c421759b167c4c15c8cdb34941d6d3512f037c25bc7f751cbb223af829d565a5a744
Type fulltextMimetype application/pdf

By organisation
Health Informatics
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 180 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 459 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf