Querétaro and the Software Recruitment Model: What the Data Confirms, What It Still Lacks

In the VAR operations room at San Siro, I learned something no refereeing manual teaches: one camera angle never tells the whole story. You have the touchline, the goal frame, the angle behind the defender, and only when those layers are stacked does the truth consent to appear. I kept that principle while reading the report that Querétaro reached Liga MX's leading group thanks to software, published by RÉCORD. I read it three times, and each time I asked myself: which angle is still missing?

On the surface, the story is tidy. A club once parked in the lower half of Mexico's table now claims a place among the league's strongest, not through blockbuster signings but through a data platform. Sporting director Álvaro de la Torre told RÉCORD that the club first defines its game model, then searches for players who fit it, rising above their fame and market price. In 2026, the U.S. fund Innovation Capital bought the club, and the methodology arrived alongside the new owner.

Liga MX is fertile ground for this approach. The league runs two short tournaments a year, Apertura and Clausura, where a hot streak can lift a team very high and drop it very fast. América, Monterrey, Tigres and Cruz Azul spend millions on stars. Querétaro cannot bid in that fight, so it chose another road: using analytical capability in place of transfer money. According to de la Torre, its platform covers more than 80 leagues, over 4 billion data points, and logs more than 15,000 actions per match.

The truly notable point lies in the sequence, not the technology. Defining the game model first and only then finding the right person is the reverse of the habit of buying the best player still on the market. In theory, that sequence closes a large gap: it reduces the risk of a signing with fine numbers that does not fit the system. I saw it immediately, because after the San Siro night I built a 37-criteria decision tree, and the biggest lesson was that a decision is only good when it stays consistent with the framework set in advance. Before I blow the whistle, I review myself.

The second layer is economics. Finding players other clubs have not yet put on their radar, then negotiating from a stronger position, is an information-asymmetry model: buy undervalued value cheaply and capture the gap. For a club that cannot win a money race, this substitutes analytical capability for capital. The logic holds. But it rests on three unverified pillars: the model's hit rate in identifying talent, the fund's patience, and the ability to sell developed players on.

A deeper signal is the arrival of U.S. investment money in Mexican football. A fund buys an underperforming club, professionalizes operations, installs a data model, and targets value on exit. If Querétaro succeeds, this could become a template for private equity across Latin American football. At the industry level, data-platform vendors also gain, because when a club boasts a platform covering 80 leagues, it is marketing an entire analytics industry growing in emerging markets.

For me, data is a verification layer, not a judge. It helps review a decision but does not replace it. If Querétaro uses software to narrow a list and leaves judgment to people, its model is sound. If it lets the algorithm decide instead, the risk shifts to a different place entirely.

The third layer is competition inside the league. Atlas is pursuing a similar analytical method, and Querétaro says it wants to go one step further. As more clubs scan data, the pool of undiscovered talent shrinks and prices climb. First-mover advantage has an expiry date. A discovery holds value only until the market learns how to price it.

One governance detail deserves a pause. A sporting director shaping the recruitment model concentrates sporting authority in one person. If the head coach wants different profiles than the blueprint, conflict is a matter of time. Every model needs a guardian, but a model resting on a single guardian is fragile.

Here I must be blunt. The article's central claim, that Querétaro is among the best in Liga MX, is asserted without a single league table, points total, or expected-goals figure. I do not trust my eyes; I trust the slow-motion replay, and here the replay is missing. The figures of 15,000 actions per match or 4 billion data points come from the club itself, unverified independently, and 15,000 actions per match is an unusual number against ordinary on-ball event data.

The short-tournament format also amplifies variance. A few hot matches in the Apertura can produce a "the model worked" story before the sample is large enough to say anything. The biggest risk here is evidentiary, not operational. When the club pushed the story to RÉCORD and put its sporting director on the program "Infiltrados", I recognized a deliberate publicity campaign. They are selling the story to investors, sponsors and future players as much as informing fans. Technology does not kill football; it kills blind faith.

Every verdict deserves one review, including the verdict of data. Querétaro is testing a road that is right in principle, but it needs at least two more transfer windows and an independent data source to prove the model creates value on the pitch. What I will watch is not today's table, but whether they can sell the players they have developed.