Trusted by 16 Champions & Europa League clubs, plus 200 more. View Pricing

Football Analytics AI Logo

Model Accuracy

Every prediction backtested against real outcomes.

Nothing enters production until it proves it works on historical data it never saw during training. We publish our accuracy metrics because the numbers are the reason clubs trust us with EUR 10,000 decisions.

89.4%
U23 xV accuracy
80%
Anti-failure precision
7 in 10
Injury flags validated
9,000+
Transfers in validation set

Position Shortlist, Squad Analytics, Player Deep Dive

xV Valuation Model

89.4% directional accuracy for U23 players

Our proprietary xV model forecasts a player's market value two years into the future. It powers the ranked shortlists, squad valuations, and deep-dive projections in our reports.

89.4%
U23 directional accuracy
79%
Overall valuation accuracy
9,000+
Historical transfers validated
21
European leagues covered

How we validate: Every prediction is tested against real transfer outcomes the model never saw during training. Accuracy is verified per league — we include the per-league breakdown in every report so you can see exactly how reliable the predictions are for your target markets.

Player Deep Dive

Anti-Failure Model

80% precision at identifying signings that won't work out

Trained on hundreds of completed transfers to learn which conditions predict a player failing to establish themselves after a move. The model evaluates maturity signals, availability history, positional risk, and destination club stability.

80%
Precision at top risk tier
2x
Failure rate for U21s vs 24+
Hundreds
Verified transfers in training set
0
False positives in comparable matching

How we validate: The model identifies the 20-25% of signings that historically fail to establish themselves at a new club. Validated against real post-transfer outcomes — players flagged as high-risk actually fail at the predicted rate.

Injury Prediction

Injury Prediction Model

7 in 10 high-risk flagged players suffer significant absence

A multi-tier model covering player profile, schedule context, and rolling workload patterns. Calibrated per league because our research showed injury patterns are league-specific — a finding most generic models miss.

70%
Precision at top risk tier
+6pp
Improvement over standard models
3-tier
Feature architecture
Local > Global
League-specific calibration wins

How we validate: Models are trained locally per league. The Premier League model is different from the Danish Superliga model. Each achieves higher accuracy than a single global model — validated against real injury data across multiple seasons.

Why we publish accuracy

01

No black boxes. Every report includes the per-league accuracy breakdown for the models used. You see exactly how reliable the predictions are for your specific markets.

02

Validated on data the models never saw. We use strict train-test splits. The accuracy numbers above come from holdout sets — real transfers and real outcomes that were hidden during model training.

03

League-specific, not one-size-fits-all. A model trained on the Premier League doesn't automatically apply to the Danish Superliga. We calibrate per league and show you which leagues our models are strongest in.

04

Continuous improvement. Models are retrained as new transfer windows complete and new outcome data becomes available. Accuracy improves every window.

Frequently Asked Questions

How accurate are football transfer predictions?+
It depends on the model and the player profile. Younger players have more predictable trajectories — our xV model achieves 89.4% directional accuracy for U23 players, validated against 9,000+ real transfer outcomes. Accuracy drops for older players and varies by league, which is why every Football Analytics AI report includes per-league breakdowns.
Can you predict if a football transfer will fail?+
Not with certainty, but statistical models can flag high-risk signings. Anti-failure models evaluate maturity signals, availability history, positional adaptation risk, and destination club stability. Our model achieves 80% precision at the top risk tier — meaning 4 out of 5 players flagged as high-risk genuinely struggle after the move.
How do football analytics companies test their models?+
The gold standard is holdout validation — training a model on historical data and testing it against real outcomes it never saw. We use strict train-test splits for all published accuracy numbers, and retrain models after each transfer window as new outcome data becomes available.
What age do football players peak in value?+
Most outfield players peak in market value between 25-27, though this varies by position — attackers tend to peak earlier than defenders. Prediction models work best for players under 23, where development curves are steeper and more predictable. Our xV model achieves 89.4% accuracy in this age band.
What data do football scouting tools use?+
Typically a mix of performance metrics, playing time data, age-adjusted development curves, league quality coefficients, and historical transfer patterns. Football Analytics AI's xV model draws on 50,000+ player profiles across 21 European leagues, calibrated per league to account for differences in competition level and market dynamics.

See the accuracy in your report.

Every report includes per-league accuracy evidence. You send a brief, we send a PDF.

Order a Report