kth.sePublications KTH
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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
A Systems-Based Approach to Talent Identification in Youth Football
KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems.
2025 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Ett systembaserat angreppssätt för talangutveckling inom ungdomsfotboll (Swedish)
Abstract [en]

Effective talent identification can benefit football clubs through first-team progressionor transfer fees. While previous studies have focused on physical, psychological, andtechnical abilities, football’s dynamic nature introduces challenges in talentidentification due to the unpredictability of events. Furthermore, many variables relyon subjective assessments, which can introduce bias or inconsistent judgments. Incollaboration with Sweden’s top-tier club AIK Fotboll, the possibility of combiningsubjective evaluation and objective performance metrics was investigated, specificallyfor U14 to U19 teams. Through a series of workshops with AIK’s youth footballstakeholders, a causal loop diagram was developed to visually represent therelationship between various objective performance metrics and subjectiveassessments. Bayesian Network models were employed to quantify their relationshipand do-calculus was applied to explore causality. Additionally, a sensitivity analysiswas conducted to assess the influence of objective performance metrics on subjectiveassessments. The Causal Loop Diagram revealed that passing metrics play a role insubjective assessments of technique and tactic, while other metrics, such astacklessuccess and foulswon, impact mental and physique evaluations. However, thecorrelation matrix and sensitivity analysis suggest a weak linear relationship betweenobjective performance metrics and subjective assessments. Even though the findingssuggest weak relationships between the two knowledge bases, they emphasize theimportance of context-induced objective metrics, and the approach can be applied toany sport.

Abstract [sv]

Effektiv talangidentifiering kan gynna fotbollsklubbar både genom att spelare tarklivet upp till A-laget och genom potentiella transferintäkter. Tidigare studier harfrämst fokuserat på fysiska, psykologiska och tekniska förmågor, men fotbollensdynamiska karaktär innebär utmaningar i talangidentifiering på grund av speletsoförutsägbarhet. Dessutom bygger många variabler på subjektiva bedömningar, vilketkan introducera bias eller ge upphov till inkonsekventa omdömen. I samarbete medAIK Fotboll, en av Sveriges främsta elitklubbar, undersöktes möjligheten attkombinera subjektiva utvärderingar med objektiva prestationsdata, specifikt förungdomslag från U14 till U19. Genom en serie workshops med aktörer inom AIK:sungdomsverksamhet utvecklades ett kausalt loopdiagram för att visuellt beskrivasambanden mellan olika objektiva prestationsmått och subjektiva bedömningar. Föratt kvantifiera dessa samband användes Bayesianska nätverksmodeller, och med hjälpav do-kalkyl analyserades eventuell kausalitet. Dessutom genomfördes enkänslighetsanalys för att undersöka hur starkt de objektiva prestationsmåtten påverkarde subjektiva utvärderingarna. Det kausala loopdiagrammet visade attpassningsrelaterade variabler påverkar subjektiva bedömningar av teknik och taktik,medan andra mått som lyckade tacklingar och vunna frisparkar påverkar mentala ochfysiska bedömningar. Samtidigt visade korrelationsmatrisen och känslighetsanalysenpå svaga linjära samband mellan objektiva mått och subjektiva bedömningar. Trotsdetta betonas vikten av att använda kontextspecifika prestationsmått, ochangreppssättet har potential att tillämpas inom andra idrotter.

Place, publisher, year, edition, pages
2025. , p. 39
Series
TRITA-CBH-GRU ; 2025:034
Keywords [en]
Talent Identification, Bayesian Networks, Causal Loop Diagrams, Sensitivity Analysis
Keywords [sv]
Talangidentifiering, Bayesianska nätverk, Kausalt loopdiagram, Känslighetsanalys
National Category
Sport and Fitness Sciences Computer Systems
Identifiers
URN: urn:nbn:se:kth:diva-365652OAI: oai:DiVA.org:kth-365652DiVA, id: diva2:1977159
Educational program
Master of Science - Sports Technology
Supervisors
Examiners
Available from: 2025-06-25 Created: 2025-06-25 Last updated: 2025-06-25Bibliographically approved

Open Access in DiVA

fulltext(3383 kB)268 downloads
File information
File name FULLTEXT01.pdfFile size 3383 kBChecksum SHA-512
3af74e3fe89632e2c494a68fedd2a7ca7961498f24037df701f7ef3e9449b0cf388afb17b987053a16aa7b4e09d71f0c0f0382dadf4b89b4167b4278f0a3d861
Type fulltextMimetype application/pdf

By organisation
Biomedical Engineering and Health Systems
Sport and Fitness SciencesComputer Systems

Search outside of DiVA

GoogleGoogle Scholar
Total: 268 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: 557 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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