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
Machine Learning for Technical Stock Analysis.
KTH, School of Computer Science and Communication (CSC).
2012 (English)Independent thesis Advanced level (professional degree), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Technical analysis has been applied to the stock market for over a century. In recent times, the technical analysis has become faster and more powerful because of computer-aided calculations and visualizations. The challenge was to take this financial engineering one step further and make it intelligent and automating stock price forecasting.

In this master's thesis, machine learning is applied to generate forecasts with a time-horizon of approximately 4.5 days, for stocks listed at Nasdaq OMXS30. A wkNN and a modified HMM were implemented. The latter failed to generate any usable forecasts, but the wkNN generated a hit rate better than chance (with high confidence). The forecasts from the wkNN were aggregated together with news-based forecasts, but the performance did not improve.

Abstract [sv]

Teknisk analys har applicerats på aktiemarknaden i över ett århundrade. På senare tid har den tekniska analysen blivit allt snabbare och kraftfullare på grund av datorstödda beräkningar och visualiseringar. Utmaningen var att ta denna financial engineering ett steg vidare och göra den intelligent och automatisera prognostisering av aktiepris.

I detta examensarbete appliceras maskininlärning för att generera prognoser med en tidshorisont på ungefär 4.5 dagar, för aktier listade på Nasdaq OMXS30. En wkNN och en modifierad HMM implementerades. Den senare misslyckades att generera några användbara prognoser, men wkNN:en genererade en hit rate bättre än slumpen (med hög konfidens). Prognoserna från wkNN:en aggregerades med nyhetsbaserade prognoser, men prestandan förbättrades inte.

Place, publisher, year, edition, pages
2012.
Series
Trita-CSC-E, ISSN 1653-5715 ; 2012:088
National Category
Computer Science
Identifiers
URN: urn:nbn:se:kth:diva-130928OAI: oai:DiVA.org:kth-130928DiVA: diva2:654374
Educational program
Master of Science in Engineering - Computer Science and Technology
Uppsok
Technology
Supervisors
Examiners
Available from: 2013-10-07 Created: 2013-10-07

Open Access in DiVA

No full text

Other links

http://www.nada.kth.se/utbildning/grukth/exjobb/rapportlistor/2012/rapporter12/cedervall_fredrik_12088.pdf
By organisation
School of Computer Science and Communication (CSC)
Computer Science

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 270 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