From data to dollar: using the wisdom of an online tipster community to improve sports betting returns
by Arne Gruettner; Thiemo Wambsganss; Andrea Back
European J. of International Management (EJIM), Vol. 15, No. 2/3, 2021

Abstract: With thousands of (online) bookmakers accepting wagers on sporting events, sports betting has become a billion-dollar business worldwide. Therefore, researchers and practitioners have gathered interest in investigating the "wisdom-of-crowds" effect in online tipster communities to predict the outcomes of sports events. We extracted 1,534,041 tips of 3484 tipsters from Blogabet.com and used this user-generated content to investigate whether there is wisdom in online tipster communities that can be used to improve betting returns. We applied state-of-the-art data mining and natural language processing techniques and tested our hypotheses using quantitative research methods. Our results demonstrate that there is indeed wisdom in such online tipster communities that can improve sports betting returns. Tipsters won 3.29% more tips than the implied win probability set by bookmakers and produced averaged yields of 3.97%. We further identified four characteristics that are significant indicators for smarter sub-crowds within the overall crowd of an online tipster community.

Online publication date: Thu, 25-Feb-2021

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the European J. of International Management (EJIM):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com