Which is the best way to compare soccer teams from different sites? For example, one soccer team in a site is named Academica Clinceni and in another FC Clinceni and in another one is Acs Fc Academica Clinceni.
Moreover, for a team can exist also the female version of the team (eg. Acs Fc Academica Clinceni (W) or Acs Fc Academica Clinceni (F)). Which is the best approach to distinguish these teams? For the first problem I used the Fuzzy String Matching, in your opinion is it right?
$\begingroup$
$\endgroup$
Add a comment
|
1 Answer
$\begingroup$
$\endgroup$
I don’t know why your question was voted down! Fuzzy matching is such a common challenge. The best approach I’ve seen is this one: https://towardsdatascience.com/fuzzy-matching-at-scale-84f2bfd0c536 It gives similar results to something like Levenshtein distance but it’s much faster. If you augment the matching approach with hand-coded regex features to spot e.g. female versus male teams, you should be able to match teams pretty well.
answered Jul 1, 2020 at 22:06