Home/Soccer Analytics/Pass Intent Imputation (Two-Step xPass)

Pass Intent Imputation (Two-Step xPass)

Passing MetricsLevel 3 — Advanced

What It Is

Modeling xPass as a two-stage problem: first predicting the intended target XY for the ~5% of passes where the recipient is unknown or blocked, then computing completion probability against that imputed target. This eliminates the short-distance completion paradox where elite players appear unable to complete 2-yard passes (because blocked/intercepted short passes get logged as failed completions with very short distances).

Correct Execution

Stage 1: For passes without a known recipient, predict intended target location from passer position, body orientation (if available), and 360 context. Stage 2: Compute completion probability against the imputed target. This two-step approach prevents the model from seeing impossibly short "failed" passes and inflating difficulty estimates for trivial passes.

Diagnostic Tree

Edges

Conventional Wisdom Is Wrong

Elite Players Appear to Fail Easy Short Passes at Impossible Rates — It's a Data Artifact

When a pass is blocked or intercepted, it registers in the data as a failed completion with a very short distance (the distance the ball actually traveled before interception, not the intended distance). Standard xPass models see these as "failed 2-yard passes" — which should be 99% completion — and conclude the player can't complete trivial passes. The real story: the player attempted a 20-yard progressive pass that was intercepted after 2 yards. Without imputing the intended target, xPass models systematically penalize the best progressive passers.

What most people do
Build xPass models on observed pass distance, which conflates blocked progressive passes with failed short passes.
What the best do
Model xPass as a two-stage problem: first predict the intended target location for passes with unknown recipients (blocked, intercepted), then compute completion probability against the imputed target. This eliminates the "short failed pass" artifact.
Why it's an edge: Any club using a standard xPass model without intent imputation is systematically undervaluing their most progressive passers and overvaluing conservative recyclers. The model literally cannot distinguish a blocked 20-yard through ball from a botched 2-yard layoff.
How to exploit: If your data provider supports pass intent (StatsBomb does for ~5% of passes), use it. For the rest, build the two-stage imputation model. When evaluating progressive passers, check if their "failed short pass" rate is anomalously high — if so, the model is likely penalizing blocked progressive passes.
Dr. Will Morgan, StatsBomb Conference, 2022-10-03. Two-step xPass approach eliminating the short-distance completion paradox.

Sources

  • Dr. Will Morgan, StatsBomb Conference 2022, YouTube, 2022-10-03