Moneyball 2.0: Sign Undervalued Footballers
A mid-budget club sells its star midfielder for €45M. It has €6M to replace him. The sporting management wants to find, in secondary leagues (Portugal, Belgium, the Netherlands, South America), players whose playing profile is as close as possible to the one leaving, but with a market value 10 times lower.
Where the money comes from
What to do now
- 1Define with the coach the variables that define the style.
- 2Generate a shortlist of 20 candidates per position.
- 3Send scouts only to that list.
For your committee
One page with the decision, the impact, the risks, the steps and the KPI to track.
The print dialog opens: choose "Save as PDF".
Watch out: more volume is not always more profit
Buying cheaply players who are similar in statistics but have not adapted to the league: the saving disappears if the player does not perform. Combine the data with scouts and adaptation analysis.
KPI for the committee
Cost per minute played and market value of the squad.
Cash
~€15M less invested in the transfer; plus about €3.7M a year less amortisation (net result, not EBITDA).
Detail for your data team
Proposed technique: K-Nearest Neighbours (KNN)
Why: The question is literally 'who is similar to this player?'. KNN measures the distance between statistical profiles and returns the closest ones. It is intuitive for sporting management ('similar in pressing and progressive passing') and with a few thousand players it is instant.
Cost of getting it wrong: A failed €6M signing plus salary can cost the season; dismissing a good player is an opportunity another club will take.
Data needed: Event data from 40 leagues: progressive passes, recoveries, pressing, dribbles, heat maps by position (per 90 minutes).; Estimated market value, age, remaining contract, injuries.; Profile of the departing player (the 'pattern' to replicate).